Add native Qwen3-VL vision weights for TI2V

model_index.json

@@ -7,7 +7,7 @@
   ],
   "text_encoder": [
     "transformers",
-    "LingBotVideoQwen3VLTextModel"
+    "LingBotVideoQwen3VLModel"
   ],
   "tokenizer": [
     "transformers",

text_encoder/config.json

@@ -1,7 +1,7 @@
 {
-  "_class_name": "LingBotVideoQwen3VLTextModel",
+  "_class_name": "LingBotVideoQwen3VLModel",
   "architectures": [
-    "LingBotVideoQwen3VLTextModel"
+    "LingBotVideoQwen3VLModel"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -10,6 +10,7 @@
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 2560,
+  "image_token_id": 151655,
   "initializer_range": 0.02,
   "intermediate_size": 9728,
   "max_position_embeddings": 262144,
@@ -31,5 +32,28 @@
   "text_len": 37698,
   "tie_word_embeddings": true,
   "use_cache": true,
+  "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,
   "vocab_size": 151936
 }

text_encoder/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa1dbe584ceb840d1a0a61aa6fc67115ab4a8ddda71fec5e50d32a58cb76cff
-size 3077750328
+oid sha256:c14586b1b1f3622067951797ad5e9ecc17c5816b7cd34d3295dcaf1c006552d5
+size 3908479800

text_encoder/model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8044936192
+    "total_size": 8875631616
   },
   "weight_map": {
     "embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -292,6 +292,321 @@
     "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"
+    "norm.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+    "visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.pos_embed.weight": "model-00002-of-00002.safetensors"
   }
 }