Add diffusers weights (modular pipeline)

Diffusers-format weights for the modular pipeline in https://github.com/huggingface/diffusers/pull/14456. Usage instructions come in a separate README PR.

.gitattributes

@@ -3,3 +3,4 @@
 *.wav filter=lfs diff=lfs merge=lfs -text
 qwen_7B/qwen3-8B-tokenizer-music/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 figures/*.png filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

condition_encoder/config.json

@@ -0,0 +1,11 @@
+{
+  "_class_name": "MiniMaxMusic3ConditionEncoder",
+  "_diffusers_version": "0.40.0.dev0",
+  "condition_hidden_dim": 4096,
+  "input_hop_length": 960,
+  "input_sampling_rate": 24000,
+  "num_condition_layers": 8,
+  "out_dim": 2048,
+  "output_hop_length": 512,
+  "output_sampling_rate": 44100
+}

condition_encoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83179c5eaa9a68a370affe0c1b96c2179f659ea4175666b31071490a202c2a4d
+size 100671852

language_model/config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 10240,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 200000
+}

language_model/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.0.dev0",
+  "use_cache": true
+}

language_model/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e95924a158b45b67cfad04fa0f0a352e5a263e69338734d7c1d558be776cc98
+size 4910103856

language_model/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde2d335eef7eafa268d35e53d4b040ee51d2f3fa727f9855b4c97d88a2892da
+size 4915960352

language_model/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6549a831637ab678a573047e7fa8fdf966998c4f45330e6eb7573d67f7b9b4c6
+size 4983068496

language_model/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c9865f357b64d3ae9f428fb98a844831e5a0aee9ed17b19bd7f7be32b964a9
+size 2359864688

language_model/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8584475648,
+    "total_size": 17168951296
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

modular_model_index.json

@@ -0,0 +1,103 @@
+{
+  "_blocks_class_name": "MiniMaxMusic3Blocks",
+  "_class_name": "MiniMaxMusic3ModularPipeline",
+  "_diffusers_version": "0.40.0.dev0",
+  "condition_encoder": [
+    "diffusers",
+    "MiniMaxMusic3ConditionEncoder",
+    {
+      "pretrained_model_name_or_path": "diffusers-internal-dev/MiniMax-Music3-Diffusers",
+      "revision": null,
+      "subfolder": "condition_encoder",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxMusic3ConditionEncoder"
+      ],
+      "variant": null
+    }
+  ],
+  "language_model": [
+    "transformers",
+    "Qwen3ForCausalLM",
+    {
+      "pretrained_model_name_or_path": "diffusers-internal-dev/MiniMax-Music3-Diffusers",
+      "revision": null,
+      "subfolder": "language_model",
+      "type_hint": [
+        "transformers",
+        "Qwen3ForCausalLM"
+      ],
+      "variant": null
+    }
+  ],
+  "rvq_depth_decoder": [
+    "diffusers",
+    "MiniMaxMusic3RVQDepthDecoder",
+    {
+      "pretrained_model_name_or_path": "diffusers-internal-dev/MiniMax-Music3-Diffusers",
+      "revision": null,
+      "subfolder": "rvq_depth_decoder",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxMusic3RVQDepthDecoder"
+      ],
+      "variant": null
+    }
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler",
+    {
+      "pretrained_model_name_or_path": "diffusers-internal-dev/MiniMax-Music3-Diffusers",
+      "revision": null,
+      "subfolder": "scheduler",
+      "type_hint": [
+        "diffusers",
+        "FlowMatchEulerDiscreteScheduler"
+      ],
+      "variant": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer",
+    {
+      "pretrained_model_name_or_path": "diffusers-internal-dev/MiniMax-Music3-Diffusers",
+      "revision": null,
+      "subfolder": "tokenizer",
+      "type_hint": [
+        "transformers",
+        "Qwen2Tokenizer"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "MiniMaxMusic3Transformer1DModel",
+    {
+      "pretrained_model_name_or_path": "diffusers-internal-dev/MiniMax-Music3-Diffusers",
+      "revision": null,
+      "subfolder": "transformer",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxMusic3Transformer1DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "vocoder": [
+    "diffusers",
+    "MiniMaxMusic3Vocoder",
+    {
+      "pretrained_model_name_or_path": "diffusers-internal-dev/MiniMax-Music3-Diffusers",
+      "revision": null,
+      "subfolder": "vocoder",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxMusic3Vocoder"
+      ],
+      "variant": null
+    }
+  ]
+}

rvq_depth_decoder/config.json

@@ -0,0 +1,11 @@
+{
+  "_class_name": "MiniMaxMusic3RVQDepthDecoder",
+  "_diffusers_version": "0.40.0.dev0",
+  "audio_vocab_size": 1024,
+  "hidden_size": 4096,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 16,
+  "num_attention_heads": 16,
+  "num_codebooks": 8,
+  "num_layers": 4
+}

rvq_depth_decoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e86ab006bb5c8d4f223205045035a1c77b2bb9c3be9a86d7e740bbafe5ddf0
+size 1292055248

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.40.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": true,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

tokenizer/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1537fa9e59a537276ecbc2e12d0438edff635a1f4a4948e679774b5feb3e610
+size 11423801

tokenizer/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "MiniMaxMusic3Transformer1DModel",
+  "_diffusers_version": "0.40.0.dev0",
+  "attention_head_dim": 64,
+  "condition_dim": 2048,
+  "ff_inner_dim": 8192,
+  "fourier_embedding_dim": 256,
+  "in_channels": 128,
+  "num_attention_heads": 32,
+  "num_layers": 36,
+  "rotary_dim": 32
+}

transformer/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1943baebe93b5d5a57e9e1f603d9cef51a73a55e7a42f52913932dc06dcf10f0
+size 4959921384

transformer/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f9e29d241e107e5a281f8b369d6db48eee983917df966c56d7b8dd0bd482c2
+size 4767750800

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,448 @@
+{
+  "metadata": {
+    "total_size": 9727623680
+  },
+  "weight_map": {
+    "postprocess_conv.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "preprocess_conv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "proj_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "time_embed.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_embed.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_embed.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_embed.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.18.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.18.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.ff_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.ff_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.ff_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.ff_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.norm1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.norm2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
+  }
+}

vocoder/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "MiniMaxMusic3Vocoder",
+  "_diffusers_version": "0.40.0.dev0",
+  "decoder_hidden_dim": 1536,
+  "decoder_input_dim": 1024,
+  "latent_channels": 128,
+  "sampling_rate": 44100,
+  "upsampling_ratios": [
+    8,
+    8,
+    4,
+    2
+  ]
+}

vocoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf0bf0560ea978ce7b5ec3e82f420a44429efef18bdfbe3c714d55ceffbe934
+size 216695272