Publish FastVideo LingBot-Video MoE 30B-A3B conversion

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+library_name: fastvideo
+pipeline_tag: text-to-video
+base_model: robbyant/lingbot-video-moe-30b-a3b
+tags:
+  - fastvideo
+  - video-generation
+  - text-to-video
+  - mixture-of-experts
+  - lingbot-video
+---
+
+# LingBot-Video MoE 30B-A3B for FastVideo
+
+This repository contains the released LingBot-Video MoE 30B-A3B base model and
+its second-stage refiner in the component layout loaded natively by FastVideo.
+The transformer, refiner, VAE, and scheduler tensors come from
+[`robbyant/lingbot-video-moe-30b-a3b`](https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b).
+The Qwen3-VL language weights are converted to FastVideo's fused text-only
+encoder layout.
+
+The current FastVideo port supports text-to-video inference. T2I, TI2V, vision
+conditioning, prompt rewriting, and automatic negative-prompt generation are
+not included in this package.
+
+## Usage
+
+Use a FastVideo revision containing
+[LingBot-Video support](https://github.com/hao-ai-lab/FastVideo/pull/1595):
+
+```python
+from fastvideo import VideoGenerator
+
+generator = VideoGenerator.from_pretrained(
+    "FastVideo/LingBot-Video-MoE-30B-A3B-Diffusers",
+    num_gpus=8,
+    sp_size=8,
+    use_fsdp_inference=True,
+    refine_enabled=True,
+    text_encoder_cpu_offload=True,
+)
+result = generator.generate({
+    "prompt": "A red fox runs through fresh snow at sunrise.",
+    "output": {"output_path": "outputs/lingbot-video", "save_video": True},
+})
+generator.shutdown()
+```
+
+The released preset generates a 121-frame 832×480 base video and optionally
+refines it to 1920×1088. Set `refine_enabled=False` when loading the model to run
+the base MoE transformer without the refiner.
+
+## Provenance
+
+- Original model: https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b
+- Original code: https://github.com/robbyant/lingbot-video
+- FastVideo port: https://github.com/hao-ai-lab/FastVideo/pull/1595
+
+The original model and this converted package are distributed under the
+Apache-2.0 license declared by the released checkpoint.

model_index.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "LingBotVideoMoePipeline",
+  "_diffusers_version": "0.39.0",
+  "scheduler": [
+    "diffusers",
+    "FlowUniPCMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "LingBotVideoQwen3VLTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen3VLProcessor"
+  ],
+  "transformer": [
+    "diffusers",
+    "LingBotVideoTransformer3DModel"
+  ],
+  "transformer_2": [
+    "diffusers",
+    "LingBotVideoTransformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLWan"
+  ],
+  "workload_type": "video-generation"
+}

scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "FlowUniPCMultistepScheduler",
+  "num_train_timesteps": 1000,
+  "shift": 1,
+  "use_dynamic_shifting": false
+}

text_encoder/config.json

@@ -0,0 +1,35 @@
+{
+  "_class_name": "LingBotVideoQwen3VLTextModel",
+  "architectures": [
+    "LingBotVideoQwen3VLTextModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 262144,
+  "mrope_interleaved": true,
+  "mrope_section": [
+    24,
+    20,
+    20
+  ],
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "output_hidden_states": true,
+  "pad_token_id": 151643,
+  "require_processor": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "text_len": 37698,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "vocab_size": 151936
+}

text_encoder/generation_config.json

@@ -0,0 +1,14 @@
+{
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "top_k": 20,
+    "top_p": 0.8,
+    "repetition_penalty": 1.0,
+    "temperature": 0.7,
+    "transformers_version": "4.56.0"
+}

text_encoder/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb97d9e4d755aeaf6851f1a9cd1f9c3f6f1ea19db32dd0b4dd59cc4e0a46e8c
+size 4967217656

text_encoder/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa1dbe584ceb840d1a0a61aa6fc67115ab4a8ddda71fec5e50d32a58cb76cff
+size 3077750328

text_encoder/model.safetensors.index.json

@@ -0,0 +1,297 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

tokenizer/README.md

@@ -0,0 +1,190 @@
+---
+license: apache-2.0
+pipeline_tag: image-text-to-text
+---
+<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+
+
+# Qwen3-VL-4B-Instruct
+
+
+Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
+
+This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.
+
+Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment.
+
+
+#### Key Enhancements:
+
+* **Visual Agent**: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks.
+
+* **Visual Coding Boost**: Generates Draw.io/HTML/CSS/JS from images/videos.
+
+* **Advanced Spatial Perception**: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI.
+
+* **Long Context & Video Understanding**: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing.
+
+* **Enhanced Multimodal Reasoning**: Excels in STEM/Math—causal analysis and logical, evidence-based answers.
+
+* **Upgraded Visual Recognition**: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc.
+
+* **Expanded OCR**: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing.
+
+* **Text Understanding on par with pure LLMs**: Seamless text–vision fusion for lossless, unified comprehension.
+
+
+#### Model Architecture Updates:
+
+<p align="center">
+    <img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_arc.jpg" width="80%"/>
+<p>
+
+
+1. **Interleaved-MRoPE**: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning.
+
+2. **DeepStack**: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment.
+
+3. **Text–Timestamp Alignment:** Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling.
+
+This is the weight repository for Qwen3-VL-4B-Instruct.
+
+
+---
+
+## Model Performance
+
+**Multimodal performance**
+
+![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_4b_8b_vl_instruct.jpg)
+
+**Pure text performance**
+![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_4b_8b_text_instruct.jpg)
+
+## Quickstart
+
+Below, we provide simple examples to show how to use Qwen3-VL with 🤖 ModelScope and 🤗 Transformers.
+
+The code of Qwen3-VL has been in the latest Hugging Face transformers and we advise you to build from source with command:
+```
+pip install git+https://github.com/huggingface/transformers
+# pip install transformers==4.57.0 # currently, V4.57.0 is not released
+```
+
+### Using 🤗 Transformers to Chat
+
+Here we show a code snippet to show how to use the chat model with `transformers`:
+
+```python
+from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
+
+# default: Load the model on the available device(s)
+model = Qwen3VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen3-VL-4B-Instruct", dtype="auto", device_map="auto"
+)
+
+# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
+# model = Qwen3VLForConditionalGeneration.from_pretrained(
+#     "Qwen/Qwen3-VL-4B-Instruct",
+#     dtype=torch.bfloat16,
+#     attn_implementation="flash_attention_2",
+#     device_map="auto",
+# )
+
+processor = AutoProcessor.from_pretrained("Qwen/Qwen/Qwen3-VL-4B-Instruct")
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+
+# Preparation for inference
+inputs = processor.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_dict=True,
+    return_tensors="pt"
+)
+
+# Inference: Generation of the output
+generated_ids = model.generate(**inputs, max_new_tokens=128)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```
+
+### Generation Hyperparameters
+#### VL
+```bash
+export greedy='false'
+export top_p=0.8
+export top_k=20
+export temperature=0.7
+export repetition_penalty=1.0
+export presence_penalty=1.5
+export out_seq_length=16384
+```
+
+#### Text
+```bash
+export greedy='false'
+export top_p=1.0
+export top_k=40
+export repetition_penalty=1.0
+export presence_penalty=2.0
+export temperature=1.0
+export out_seq_length=32768
+```
+
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen3technicalreport,
+      title={Qwen3 Technical Report}, 
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388}, 
+}
+
+@article{Qwen2.5-VL,
+  title={Qwen2.5-VL Technical Report},
+  author={Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Zesen and Zhang, Hang and Yang, Zhibo and Xu, Haiyang and Lin, Junyang},
+  journal={arXiv preprint arXiv:2502.13923},
+  year={2025}
+}
+
+@article{Qwen2VL,
+  title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
+  author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
+  journal={arXiv preprint arXiv:2409.12191},
+  year={2024}
+}
+
+@article{Qwen-VL,
+  title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
+  author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
+  journal={arXiv preprint arXiv:2308.12966},
+  year={2023}
+}
+```

tokenizer/chat_template.json

@@ -0,0 +1,4 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}
+  

tokenizer/config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

tokenizer/configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

tokenizer/generation_config.json

@@ -0,0 +1,14 @@
+{
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "top_k": 20,
+    "top_p": 0.8,
+    "repetition_penalty": 1.0,
+    "temperature": 0.7,
+    "transformers_version": "4.56.0"
+}

tokenizer/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

tokenizer/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

transformer/config.json

@@ -0,0 +1,44 @@
+{
+  "_class_name": "LingBotVideoTransformer3DModel",
+  "_diffusers_version": "0.37.0",
+  "axes_dims": [
+    32,
+    48,
+    48
+  ],
+  "axes_lens": [
+    4096,
+    512,
+    512
+  ],
+  "decoder_sparse_step": 1,
+  "depth": 48,
+  "freq_dim": 256,
+  "hidden_size": 2048,
+  "in_channels": 16,
+  "intermediate_size": 6144,
+  "mlp_only_layers": [],
+  "moe_intermediate_size": 768,
+  "n_group": 4,
+  "n_shared_experts": 1,
+  "norm_eps": 1e-06,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "out_bias": true,
+  "out_channels": 16,
+  "patch_embed_bias": true,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "qkv_bias": false,
+  "rope_theta": 256.0,
+  "routed_scaling_factor": 2.5,
+  "score_func": "sigmoid",
+  "text_dim": 2560,
+  "timestep_mlp_bias": true,
+  "topk_group": 2
+}

transformer/diffusion_pytorch_model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20447e646d912ec373901782b0f08891e91dcc0580f3c1fa0435f0db9e228f7
+size 4735021800

transformer/diffusion_pytorch_model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35d97c040e8892f4a2a05a0f4749104e2a1add9bfc0b778988aa0e758b58522
+size 4605704096

transformer/diffusion_pytorch_model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f251fd8253966ff108cc6f52cda8debafbc34b74e52b9e8cd2100955c15443b
+size 4605704128

transformer/diffusion_pytorch_model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1bcacd77bbc678f85d05f6f807dc9e05edea2335e714865ad4ec8144a8c183
+size 4998898704

transformer/diffusion_pytorch_model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42da6fece19fd1f140ff9233d79445bef5c1fe5bd436bdf2615ad1285f18571
+size 4999967560

transformer/diffusion_pytorch_model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcc880321705c16586ee6f4a82d18336c9ca8989a1a6626c90093dd0e57d719
+size 4999968760

transformer/diffusion_pytorch_model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2160ee9b20678165f40e4797b4876ad7dc7912d483dd835894c0acc627cf0423
+size 4999968760

transformer/diffusion_pytorch_model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3d555060bf4ab26a2e21fb980e408c42c4921732f2ad3e39877849ccbd12ea
+size 4998854096

transformer/diffusion_pytorch_model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4038d735dd6a531c2781bd0496ebf3e4b980309a224ebc10c8f5aa0df5e07d7b
+size 4605704160

transformer/diffusion_pytorch_model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94095348f9bf7c21bec7cd21acb49077e4526ca2c574fbc18f31717448872a1
+size 4605704176

transformer/diffusion_pytorch_model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4b95693f4fc0f38b1dd52fc42d77ad6043e62e3e70f47ea207d78625a637d3
+size 4605704176

transformer/diffusion_pytorch_model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb274d2e725b80d98764cfa0912c3cb0bfe787603f5b8f21297c5e6f38150a2
+size 4998898704

transformer/diffusion_pytorch_model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4368d70798627438e3408d218f25509af3ac3facac8b0d02095d832f4795e8c6
+size 2512787328

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,984 @@
+{
+  "metadata": {
+    "total_size": 60272785536
+  },
+  "weight_map": {
+    "blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_out.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.experts.w1": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.experts.w2": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.experts.w3": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.router.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.norm_post_attn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.norm_post_ffn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.scale_shift_table": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_out.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.experts.w1": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.experts.w2": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.experts.w3": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.router.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.norm_post_attn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.norm_post_ffn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.scale_shift_table": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_out.bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.experts.w1": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.experts.w2": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.experts.w3": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.router.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.norm1.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.norm2.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.norm_post_attn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.norm_post_ffn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.scale_shift_table": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_out.bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.ffn.experts.w1": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.experts.w2": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.experts.w3": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.ffn.router.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.norm1.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.norm2.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.norm_post_attn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.norm_post_ffn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.scale_shift_table": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_out.bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.experts.w1": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.experts.w2": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.experts.w3": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.router.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.norm1.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.norm2.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.norm_post_attn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.norm_post_ffn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.scale_shift_table": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_out.bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.experts.w1": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.experts.w2": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.experts.w3": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.router.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.norm1.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.norm2.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.norm_post_attn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.norm_post_ffn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.scale_shift_table": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_out.bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.experts.w1": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.experts.w2": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.experts.w3": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.router.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.norm1.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.norm2.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.norm_post_attn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.norm_post_ffn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.scale_shift_table": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.to_out.bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.ffn.experts.w1": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.experts.w2": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.experts.w3": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.router.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.norm1.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.norm2.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.norm_post_attn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.norm_post_ffn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.scale_shift_table": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_out.bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.experts.w1": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.experts.w2": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.experts.w3": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.router.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.norm1.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.norm2.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.norm_post_attn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.norm_post_ffn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.scale_shift_table": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_out.bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.experts.w1": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.experts.w2": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.experts.w3": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.router.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.norm1.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.norm2.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.norm_post_attn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.norm_post_ffn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.scale_shift_table": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_out.bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.experts.w1": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.experts.w2": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.experts.w3": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.router.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.norm1.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.norm2.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.norm_post_attn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.norm_post_ffn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.scale_shift_table": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.19.attn.to_out.bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.experts.w1": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.experts.w2": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.experts.w3": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.router.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.norm1.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.19.norm2.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.norm_post_attn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.norm_post_ffn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.scale_shift_table": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_out.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.experts.w1": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.experts.w2": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.experts.w3": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.router.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.norm_post_attn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.norm_post_ffn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.scale_shift_table": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_out.bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.experts.w1": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.experts.w2": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.experts.w3": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.router.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.norm1.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.norm2.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.norm_post_attn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.norm_post_ffn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.scale_shift_table": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_out.bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.experts.w1": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.experts.w2": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.experts.w3": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.router.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.norm1.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.norm2.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.norm_post_attn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.norm_post_ffn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.scale_shift_table": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_out.bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.experts.w1": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.experts.w2": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.experts.w3": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.router.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.norm1.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.norm2.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.norm_post_attn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.norm_post_ffn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.scale_shift_table": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.to_out.bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.experts.w1": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.experts.w2": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.experts.w3": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.router.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.norm1.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.23.norm2.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.norm_post_attn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.norm_post_ffn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.scale_shift_table": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_out.bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.experts.w1": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.experts.w2": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.experts.w3": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.router.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.norm1.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.norm2.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.norm_post_attn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.norm_post_ffn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.scale_shift_table": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_out.bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.experts.w1": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.experts.w2": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.experts.w3": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.router.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.norm1.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.norm2.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.norm_post_attn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.norm_post_ffn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.scale_shift_table": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_out.bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.experts.w1": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.experts.w2": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.experts.w3": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.router.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.norm1.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.norm2.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.norm_post_attn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.norm_post_ffn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.scale_shift_table": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_out.bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.experts.w1": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.experts.w2": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.experts.w3": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.router.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.norm1.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.27.norm2.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.norm_post_attn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.norm_post_ffn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.scale_shift_table": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.28.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_out.bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.experts.w1": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.experts.w2": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.experts.w3": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.router.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.norm1.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.norm2.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.norm_post_attn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.norm_post_ffn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.scale_shift_table": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_out.bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.experts.w1": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.experts.w2": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.experts.w3": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.router.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.norm1.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.norm2.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.norm_post_attn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.norm_post_ffn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.scale_shift_table": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_out.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.experts.w1": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.experts.w2": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.experts.w3": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.router.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.norm1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.norm2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.norm_post_attn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.norm_post_ffn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.scale_shift_table": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.30.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_out.bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.experts.w1": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.experts.w2": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.experts.w3": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.router.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.30.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.30.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.30.norm1.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.norm2.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.norm_post_attn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.norm_post_ffn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.30.scale_shift_table": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.31.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_out.bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_out.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.experts.w1": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.experts.w2": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.experts.w3": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.router.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.norm1.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.norm2.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.norm_post_attn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.norm_post_ffn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.scale_shift_table": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_out.bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_out.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.experts.w1": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.experts.w2": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.experts.w3": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.router.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.norm1.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.norm2.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.norm_post_attn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.norm_post_ffn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.scale_shift_table": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_out.bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_out.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.experts.w1": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.experts.w2": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.experts.w3": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.router.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.norm1.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.norm2.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.norm_post_attn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.norm_post_ffn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.scale_shift_table": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_out.bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_out.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.experts.w1": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.experts.w2": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.experts.w3": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.router.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.norm1.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.norm2.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.norm_post_attn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.norm_post_ffn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.scale_shift_table": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.35.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_out.bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_out.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.experts.w1": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.experts.w2": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.experts.w3": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.router.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.norm1.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.norm2.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.norm_post_attn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.norm_post_ffn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.scale_shift_table": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_out.bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_out.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.experts.w1": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.experts.w2": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.experts.w3": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.router.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.norm1.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.norm2.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.norm_post_attn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.norm_post_ffn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.scale_shift_table": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_out.bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_out.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.experts.w1": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.experts.w2": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.experts.w3": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.router.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.norm1.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.norm2.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.norm_post_attn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.norm_post_ffn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.scale_shift_table": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_out.bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_out.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.ffn.experts.w1": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.ffn.experts.w2": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.ffn.experts.w3": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.ffn.router.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.norm1.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.norm2.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.norm_post_attn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.norm_post_ffn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.scale_shift_table": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.39.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_out.bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_out.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.experts.w1": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.experts.w2": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.experts.w3": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.router.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.norm1.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.norm2.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.norm_post_attn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.norm_post_ffn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.scale_shift_table": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_out.bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.experts.w1": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.experts.w2": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.experts.w3": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.router.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.norm1.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.norm2.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.norm_post_attn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.norm_post_ffn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.scale_shift_table": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.40.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_out.bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_out.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.experts.w1": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.experts.w2": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.experts.w3": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.router.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.norm1.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.norm2.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.norm_post_attn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.norm_post_ffn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.scale_shift_table": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_out.bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_out.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.experts.w1": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.experts.w2": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.experts.w3": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.router.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.norm1.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.norm2.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.norm_post_attn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.norm_post_ffn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.scale_shift_table": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_out.bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_out.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.ffn.experts.w1": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.experts.w2": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.experts.w3": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.ffn.router.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.norm1.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.norm2.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.norm_post_attn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.norm_post_ffn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.scale_shift_table": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.43.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_out.bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_out.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.experts.w1": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.experts.w2": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.experts.w3": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.router.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.norm1.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.norm2.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.norm_post_attn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.norm_post_ffn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.scale_shift_table": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_out.bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_out.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.experts.w1": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.experts.w2": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.experts.w3": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.router.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.norm1.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.norm2.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.norm_post_attn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.norm_post_ffn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.scale_shift_table": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_out.bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_out.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.experts.w1": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.experts.w2": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.experts.w3": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.router.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.norm1.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.norm2.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.norm_post_attn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.norm_post_ffn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.scale_shift_table": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.to_out.bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.attn.to_out.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.ffn.experts.w1": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.experts.w2": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.experts.w3": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.router.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.norm1.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.norm2.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.norm_post_attn.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.norm_post_ffn.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.scale_shift_table": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.47.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_out.bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_out.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.experts.w1": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.experts.w2": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.experts.w3": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.router.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.norm1.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.norm2.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.norm_post_attn.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.norm_post_ffn.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.scale_shift_table": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_out.bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.experts.w1": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.experts.w2": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.experts.w3": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.router.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.norm1.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.norm2.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.norm_post_attn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.norm_post_ffn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.scale_shift_table": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_out.bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.experts.w1": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.experts.w2": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.experts.w3": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.router.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.norm1.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.norm2.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.norm_post_attn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.norm_post_ffn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.scale_shift_table": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_out.bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.ffn.experts.w1": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.ffn.experts.w2": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.ffn.experts.w3": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.ffn.router.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.norm1.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.norm2.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.norm_post_attn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.norm_post_ffn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.scale_shift_table": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_out.bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.experts.w1": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.experts.w2": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.experts.w3": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.router.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.norm1.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.norm2.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.norm_post_attn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.norm_post_ffn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.scale_shift_table": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_out.bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.experts.w1": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.experts.w2": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.experts.w3": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.router.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.norm1.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.norm2.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.norm_post_attn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.norm_post_ffn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.scale_shift_table": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "norm_out_modulation.1.bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "norm_out_modulation.1.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "patch_embedder.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "patch_embedder.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "text_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "text_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "text_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "text_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "text_embedder.norm.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_modulation.1.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_modulation.1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors"
+  }
+}

transformer_2/config.json

@@ -0,0 +1,44 @@
+{
+  "_class_name": "LingBotVideoTransformer3DModel",
+  "_diffusers_version": "0.37.1",
+  "axes_dims": [
+    32,
+    48,
+    48
+  ],
+  "axes_lens": [
+    4096,
+    512,
+    512
+  ],
+  "decoder_sparse_step": 1,
+  "depth": 48,
+  "freq_dim": 256,
+  "hidden_size": 2048,
+  "in_channels": 16,
+  "intermediate_size": 6144,
+  "mlp_only_layers": [],
+  "moe_intermediate_size": 768,
+  "n_group": 4,
+  "n_shared_experts": 1,
+  "norm_eps": 1e-06,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "out_bias": true,
+  "out_channels": 16,
+  "patch_embed_bias": true,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "qkv_bias": false,
+  "rope_theta": 256.0,
+  "routed_scaling_factor": 2.5,
+  "score_func": "sigmoid",
+  "text_dim": 2560,
+  "timestep_mlp_bias": true,
+  "topk_group": 2
+}

transformer_2/diffusion_pytorch_model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cba4b74ca58183919dd95b32638ef46415fe54efc029b697b5c4024a52a51e4
+size 4735021800

transformer_2/diffusion_pytorch_model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9d6c7d718dee6ddf657f41a4d8861adbc89402fd31b0b06652a8d1bf47e005
+size 4605704096

transformer_2/diffusion_pytorch_model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094f71b5f3bd6533288b1432ace41514b9a2d114216289f43cf7bd219ede61fe
+size 4605704128

transformer_2/diffusion_pytorch_model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ac25b888b7464c489338d1b8e6398425d1f94a33eacb852c5191bb465c832d
+size 4998898704

transformer_2/diffusion_pytorch_model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c006a94f51428b541f0be4d50d476bca4f6fcc10e7ed7cd8ae86cfed9cc7ae
+size 4999967560

transformer_2/diffusion_pytorch_model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3061897749eb2e244f674de7fe95e17258e3b1f7efceaf7b0d102a2497b759
+size 4999968760

transformer_2/diffusion_pytorch_model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17d91687b3670cb9718f07fff9fea1468dc5a2c28e8b99494bd8c7a2fb215f8
+size 4999968760

transformer_2/diffusion_pytorch_model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e1024335167e082ba81114642fd6a49224275130bb4625d587d8a96d530d81
+size 4998854096

transformer_2/diffusion_pytorch_model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306f3a987f31ddb57e35ffe02a23d33be1abcd8efb9c4bc3a376a3a9e979c332
+size 4605704160

transformer_2/diffusion_pytorch_model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba15ca090369e0b63badbcd6e4b6b6258be515d917903d680f9f39c003ecc1cd
+size 4605704176

transformer_2/diffusion_pytorch_model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1bc938c480a288f2661fdbee677d582bf83cc52ae2bb669ac69a38f2213195
+size 4605704176

transformer_2/diffusion_pytorch_model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e23f81780ecc2fd503e3c4b67ba62193dbf1ec23a67678cb632432f6cefd0d
+size 4998898704

transformer_2/diffusion_pytorch_model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98942267fcf22a871def9f5fe6e90fd66770a4003047b7bc805f35b354bc4dc3
+size 2512787328

transformer_2/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,984 @@
+{
+  "metadata": {
+    "total_size": 60272785536
+  },
+  "weight_map": {
+    "blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_out.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.experts.w1": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.experts.w2": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.experts.w3": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.router.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.norm_post_attn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.norm_post_ffn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.0.scale_shift_table": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_out.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.experts.w1": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.experts.w2": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.experts.w3": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.router.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.norm_post_attn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.norm_post_ffn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.1.scale_shift_table": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_out.bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.experts.w1": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.experts.w2": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.experts.w3": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.router.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.norm1.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.norm2.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.norm_post_attn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.norm_post_ffn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.10.scale_shift_table": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_out.bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.ffn.experts.w1": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.experts.w2": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.experts.w3": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.ffn.router.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.norm1.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.norm2.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.norm_post_attn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.11.norm_post_ffn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.11.scale_shift_table": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_out.bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.experts.w1": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.experts.w2": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.experts.w3": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.router.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.norm1.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.norm2.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.norm_post_attn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.norm_post_ffn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.12.scale_shift_table": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_out.bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.experts.w1": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.experts.w2": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.experts.w3": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.router.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.norm1.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.norm2.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.norm_post_attn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.norm_post_ffn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.13.scale_shift_table": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_out.bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.experts.w1": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.experts.w2": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.experts.w3": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.router.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.norm1.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.norm2.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.norm_post_attn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.norm_post_ffn.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.14.scale_shift_table": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.to_out.bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.ffn.experts.w1": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.experts.w2": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.experts.w3": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.router.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.norm1.weight": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.15.norm2.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.norm_post_attn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.norm_post_ffn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.15.scale_shift_table": "diffusion_pytorch_model-00004-of-00013.safetensors",
+    "blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_out.bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.experts.w1": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.experts.w2": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.experts.w3": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.router.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.norm1.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.norm2.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.norm_post_attn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.norm_post_ffn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.16.scale_shift_table": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_out.bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.experts.w1": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.experts.w2": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.experts.w3": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.router.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.norm1.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.norm2.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.norm_post_attn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.norm_post_ffn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.17.scale_shift_table": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_out.bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.experts.w1": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.experts.w2": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.experts.w3": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.router.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.norm1.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.norm2.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.norm_post_attn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.norm_post_ffn.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.18.scale_shift_table": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.19.attn.to_out.bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.experts.w1": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.experts.w2": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.experts.w3": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.router.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.norm1.weight": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.19.norm2.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.norm_post_attn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.norm_post_ffn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.19.scale_shift_table": "diffusion_pytorch_model-00005-of-00013.safetensors",
+    "blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_out.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.experts.w1": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.experts.w2": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.experts.w3": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.router.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.norm_post_attn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.norm_post_ffn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.2.scale_shift_table": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_out.bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.experts.w1": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.experts.w2": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.experts.w3": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.router.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.norm1.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.norm2.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.norm_post_attn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.norm_post_ffn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.20.scale_shift_table": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_out.bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.experts.w1": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.experts.w2": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.experts.w3": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.router.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.norm1.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.norm2.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.norm_post_attn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.norm_post_ffn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.21.scale_shift_table": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_out.bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.experts.w1": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.experts.w2": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.experts.w3": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.router.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.norm1.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.norm2.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.norm_post_attn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.norm_post_ffn.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.22.scale_shift_table": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.to_out.bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.experts.w1": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.experts.w2": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.experts.w3": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.router.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.norm1.weight": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.23.norm2.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.norm_post_attn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.norm_post_ffn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.23.scale_shift_table": "diffusion_pytorch_model-00006-of-00013.safetensors",
+    "blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_out.bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.experts.w1": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.experts.w2": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.experts.w3": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.router.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.norm1.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.norm2.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.norm_post_attn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.norm_post_ffn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.24.scale_shift_table": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_out.bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.experts.w1": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.experts.w2": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.experts.w3": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.router.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.norm1.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.norm2.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.norm_post_attn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.norm_post_ffn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.25.scale_shift_table": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_out.bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.experts.w1": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.experts.w2": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.experts.w3": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.router.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.norm1.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.norm2.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.norm_post_attn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.norm_post_ffn.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.26.scale_shift_table": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_out.bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.experts.w1": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.experts.w2": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.experts.w3": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.router.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.norm1.weight": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.27.norm2.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.norm_post_attn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.norm_post_ffn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.27.scale_shift_table": "diffusion_pytorch_model-00007-of-00013.safetensors",
+    "blocks.28.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_out.bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.experts.w1": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.experts.w2": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.experts.w3": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.router.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.norm1.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.norm2.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.norm_post_attn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.norm_post_ffn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.28.scale_shift_table": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_out.bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.experts.w1": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.experts.w2": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.experts.w3": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.router.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.norm1.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.norm2.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.norm_post_attn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.norm_post_ffn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.29.scale_shift_table": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_out.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.experts.w1": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.experts.w2": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.experts.w3": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.router.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.norm1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.norm2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.norm_post_attn.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.3.norm_post_ffn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.3.scale_shift_table": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "blocks.30.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_out.bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.experts.w1": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.experts.w2": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.experts.w3": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.router.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.30.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.30.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.30.norm1.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.norm2.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.norm_post_attn.weight": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.30.norm_post_ffn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.30.scale_shift_table": "diffusion_pytorch_model-00008-of-00013.safetensors",
+    "blocks.31.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_out.bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_out.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.experts.w1": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.experts.w2": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.experts.w3": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.router.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.norm1.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.norm2.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.norm_post_attn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.norm_post_ffn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.31.scale_shift_table": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_out.bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_out.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.experts.w1": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.experts.w2": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.experts.w3": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.router.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.norm1.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.norm2.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.norm_post_attn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.norm_post_ffn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.32.scale_shift_table": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_out.bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_out.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.experts.w1": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.experts.w2": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.experts.w3": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.router.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.norm1.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.norm2.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.norm_post_attn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.norm_post_ffn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.33.scale_shift_table": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_out.bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_out.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.experts.w1": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.experts.w2": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.experts.w3": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.router.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.norm1.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.norm2.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.norm_post_attn.weight": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.34.norm_post_ffn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.34.scale_shift_table": "diffusion_pytorch_model-00009-of-00013.safetensors",
+    "blocks.35.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_out.bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_out.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.experts.w1": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.experts.w2": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.experts.w3": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.router.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.norm1.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.norm2.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.norm_post_attn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.norm_post_ffn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.35.scale_shift_table": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_out.bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_out.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.experts.w1": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.experts.w2": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.experts.w3": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.router.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.norm1.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.norm2.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.norm_post_attn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.norm_post_ffn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.36.scale_shift_table": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_out.bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_out.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.experts.w1": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.experts.w2": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.experts.w3": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.router.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.norm1.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.norm2.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.norm_post_attn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.norm_post_ffn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.37.scale_shift_table": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_out.bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_out.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.ffn.experts.w1": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.ffn.experts.w2": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.ffn.experts.w3": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.ffn.router.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.norm1.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.norm2.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.norm_post_attn.weight": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.38.norm_post_ffn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.38.scale_shift_table": "diffusion_pytorch_model-00010-of-00013.safetensors",
+    "blocks.39.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_out.bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_out.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.experts.w1": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.experts.w2": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.experts.w3": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.router.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.norm1.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.norm2.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.norm_post_attn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.norm_post_ffn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.39.scale_shift_table": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_out.bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.experts.w1": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.experts.w2": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.experts.w3": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.router.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.norm1.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.norm2.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.norm_post_attn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.norm_post_ffn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.4.scale_shift_table": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.40.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_out.bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_out.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.experts.w1": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.experts.w2": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.experts.w3": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.router.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.norm1.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.norm2.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.norm_post_attn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.norm_post_ffn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.40.scale_shift_table": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_out.bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_out.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.experts.w1": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.experts.w2": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.experts.w3": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.router.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.norm1.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.norm2.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.norm_post_attn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.norm_post_ffn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.41.scale_shift_table": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_out.bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_out.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.ffn.experts.w1": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.experts.w2": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.experts.w3": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.ffn.router.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.norm1.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.norm2.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.norm_post_attn.weight": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.42.norm_post_ffn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.42.scale_shift_table": "diffusion_pytorch_model-00011-of-00013.safetensors",
+    "blocks.43.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_out.bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_out.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.experts.w1": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.experts.w2": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.experts.w3": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.router.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.norm1.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.norm2.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.norm_post_attn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.norm_post_ffn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.43.scale_shift_table": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_out.bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_out.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.experts.w1": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.experts.w2": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.experts.w3": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.router.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.norm1.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.norm2.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.norm_post_attn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.norm_post_ffn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.44.scale_shift_table": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_out.bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_out.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.experts.w1": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.experts.w2": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.experts.w3": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.router.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.norm1.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.norm2.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.norm_post_attn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.norm_post_ffn.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.45.scale_shift_table": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.to_out.bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.attn.to_out.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.ffn.experts.w1": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.experts.w2": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.experts.w3": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.router.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.norm1.weight": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.46.norm2.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.norm_post_attn.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.norm_post_ffn.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.46.scale_shift_table": "diffusion_pytorch_model-00012-of-00013.safetensors",
+    "blocks.47.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_out.bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_out.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.experts.w1": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.experts.w2": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.experts.w3": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.router.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.norm1.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.norm2.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.norm_post_attn.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.norm_post_ffn.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.47.scale_shift_table": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_out.bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.experts.w1": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.experts.w2": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.experts.w3": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.router.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.norm1.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.norm2.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.norm_post_attn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.norm_post_ffn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.5.scale_shift_table": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_out.bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.experts.w1": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.experts.w2": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.experts.w3": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.router.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.norm1.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.norm2.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.norm_post_attn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.norm_post_ffn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.6.scale_shift_table": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_out.bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.ffn.experts.w1": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.ffn.experts.w2": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.ffn.experts.w3": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.ffn.router.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.norm1.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.norm2.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.norm_post_attn.weight": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.7.norm_post_ffn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.7.scale_shift_table": "diffusion_pytorch_model-00002-of-00013.safetensors",
+    "blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_out.bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.experts.w1": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.experts.w2": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.experts.w3": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.router.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.norm1.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.norm2.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.norm_post_attn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.norm_post_ffn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.8.scale_shift_table": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_out.bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.experts.w1": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.experts.w2": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.experts.w3": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.router.e_score_correction_bias": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.router.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.shared_experts.down_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.shared_experts.gate_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.ffn.shared_experts.up_proj.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.norm1.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.norm2.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.norm_post_attn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.norm_post_ffn.weight": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "blocks.9.scale_shift_table": "diffusion_pytorch_model-00003-of-00013.safetensors",
+    "norm_out_modulation.1.bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "norm_out_modulation.1.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "patch_embedder.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "patch_embedder.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00013-of-00013.safetensors",
+    "text_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "text_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "text_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "text_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "text_embedder.norm.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_modulation.1.bias": "diffusion_pytorch_model-00001-of-00013.safetensors",
+    "time_modulation.1.weight": "diffusion_pytorch_model-00001-of-00013.safetensors"
+  }
+}

vae/config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "AutoencoderKLWan",
+  "_diffusers_version": "0.33.0.dev0",
+  "attn_scales": [],
+  "base_dim": 96,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "latents_mean": [
+    -0.7571,
+    -0.7089,
+    -0.9113,
+    0.1075,
+    -0.1745,
+    0.9653,
+    -0.1517,
+    1.5508,
+    0.4134,
+    -0.0715,
+    0.5517,
+    -0.3632,
+    -0.1922,
+    -0.9497,
+    0.2503,
+    -0.2921
+  ],
+  "latents_std": [
+    2.8184,
+    1.4541,
+    2.3275,
+    2.6558,
+    1.2196,
+    1.7708,
+    2.6052,
+    2.0743,
+    3.2687,
+    2.1526,
+    2.8652,
+    1.5579,
+    1.6382,
+    1.1253,
+    2.8251,
+    1.916
+  ],
+  "num_res_blocks": 2,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 16
+}