diff --git "a/sft/smoe/model.safetensors.index.json" "b/sft/smoe/model.safetensors.index.json" deleted file mode 100644--- "a/sft/smoe/model.safetensors.index.json" +++ /dev/null @@ -1,1005 +0,0 @@ -{ - "metadata": { - "total_size": 10206819456 - }, - "weight_map": { - "lm_head.weight": "model-00003-of-00003.safetensors", - "model.embed_tokens.weight": "model-00001-of-00003.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", - "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", - "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", - "model.mm_projector.moelayer.experts.0.0.bias": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.0.0.weight": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.0.2.bias": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.0.2.weight": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.1.0.bias": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.1.0.weight": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.1.2.bias": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.1.2.weight": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.2.0.bias": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.2.0.weight": "model-00002-of-00003.safetensors", - "model.mm_projector.moelayer.experts.2.2.bias": "model-00003-of-00003.safetensors", - "model.mm_projector.moelayer.experts.2.2.weight": "model-00003-of-00003.safetensors", - "model.mm_projector.moelayer.experts.3.0.bias": "model-00003-of-00003.safetensors", - "model.mm_projector.moelayer.experts.3.0.weight": "model-00003-of-00003.safetensors", - "model.mm_projector.moelayer.experts.3.2.bias": "model-00003-of-00003.safetensors", - "model.mm_projector.moelayer.experts.3.2.weight": "model-00003-of-00003.safetensors", - "model.mm_projector.moelayer.gate.weight": "model-00003-of-00003.safetensors", - "model.norm.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.0.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.0.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.0.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.0.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.1.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.1.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.1.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.1.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.2.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.2.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.2.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.2.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.3.fc1.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.3.fc1.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.3.fc2.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.experts.3.fc2.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.moelayer.gate.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", - "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors" - } -}