{
  "metadata": {
    "total_size": 9561071794
  },
  "weight_map": {
    "lm_head.weight": "model-00002-of-00002.safetensors",
    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
    "model.mm_projector.encoder_mlp.0.bias": "model-00002-of-00002.safetensors",
    "model.mm_projector.encoder_mlp.0.weight": "model-00002-of-00002.safetensors",
    "model.mm_projector.encoder_mlp.1.1.bias": "model-00002-of-00002.safetensors",
    "model.mm_projector.encoder_mlp.1.1.weight": "model-00002-of-00002.safetensors",
    "model.mm_projector.encoder_mlp.2.1.bias": "model-00002-of-00002.safetensors",
    "model.mm_projector.encoder_mlp.2.1.weight": "model-00002-of-00002.safetensors",
    "model.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.image_pos_embed.column_embeddings.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.image_pos_embed.row_embeddings.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.image_proj_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.image_proj_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.image_projection": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.final_logits_bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.lm_head.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.embed_positions.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.embed_tokens.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layernorm_embedding.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layernorm_embedding.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.embed_positions.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.embed_tokens.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layernorm_embedding.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layernorm_embedding.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.final_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.final_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.encoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.language_model.model.shared.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.0.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.0.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.0.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.0.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.1.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.1.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.1.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.1.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.2.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.2.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.2.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.2.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.3.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.3.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.3.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_tower.convs.3.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.visual_temporal_embed.pos_idx_to_embed": "model-00002-of-00002.safetensors"
  }
}