{ "metadata": { "total_size": 541812736 }, "weight_map": { "image_pos_embed.column_embeddings.weight": "model.safetensors", "image_pos_embed.row_embeddings.weight": "model.safetensors", "image_proj_norm.bias": "model.safetensors", "image_proj_norm.weight": "model.safetensors", "image_projection": "model.safetensors", "language_model.lm_head.weight": "model.safetensors", "language_model.model.decoder.embed_positions.weight": "model.safetensors", "language_model.model.decoder.layernorm_embedding.bias": "model.safetensors", "language_model.model.decoder.layernorm_embedding.weight": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.0.fc1.bias": "model.safetensors", "language_model.model.decoder.layers.0.fc1.weight": "model.safetensors", "language_model.model.decoder.layers.0.fc2.bias": "model.safetensors", "language_model.model.decoder.layers.0.fc2.weight": "model.safetensors", "language_model.model.decoder.layers.0.final_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.0.final_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.0.self_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.0.self_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.0.self_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.0.self_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.0.self_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.0.self_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.0.self_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.0.self_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.0.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.0.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.1.fc1.bias": "model.safetensors", "language_model.model.decoder.layers.1.fc1.weight": "model.safetensors", "language_model.model.decoder.layers.1.fc2.bias": "model.safetensors", "language_model.model.decoder.layers.1.fc2.weight": "model.safetensors", "language_model.model.decoder.layers.1.final_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.1.final_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.1.self_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.1.self_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.1.self_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.1.self_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.1.self_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.1.self_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.1.self_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.1.self_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.1.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.1.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.2.fc1.bias": "model.safetensors", "language_model.model.decoder.layers.2.fc1.weight": "model.safetensors", "language_model.model.decoder.layers.2.fc2.bias": "model.safetensors", "language_model.model.decoder.layers.2.fc2.weight": "model.safetensors", "language_model.model.decoder.layers.2.final_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.2.final_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.2.self_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.2.self_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.2.self_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.2.self_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.2.self_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.2.self_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.2.self_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.2.self_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.2.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.2.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.3.fc1.bias": "model.safetensors", "language_model.model.decoder.layers.3.fc1.weight": "model.safetensors", "language_model.model.decoder.layers.3.fc2.bias": "model.safetensors", "language_model.model.decoder.layers.3.fc2.weight": "model.safetensors", "language_model.model.decoder.layers.3.final_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.3.final_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.3.self_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.3.self_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.3.self_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.3.self_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.3.self_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.3.self_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.3.self_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.3.self_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.3.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.3.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.4.encoder_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.4.fc1.bias": "model.safetensors", "language_model.model.decoder.layers.4.fc1.weight": "model.safetensors", "language_model.model.decoder.layers.4.fc2.bias": "model.safetensors", "language_model.model.decoder.layers.4.fc2.weight": "model.safetensors", "language_model.model.decoder.layers.4.final_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.4.final_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.4.self_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.4.self_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.4.self_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.4.self_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.4.self_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.4.self_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.4.self_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.4.self_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.4.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.4.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.5.encoder_attn_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.5.fc1.bias": "model.safetensors", "language_model.model.decoder.layers.5.fc1.weight": "model.safetensors", "language_model.model.decoder.layers.5.fc2.bias": "model.safetensors", "language_model.model.decoder.layers.5.fc2.weight": "model.safetensors", "language_model.model.decoder.layers.5.final_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.5.final_layer_norm.weight": "model.safetensors", "language_model.model.decoder.layers.5.self_attn.k_proj.bias": "model.safetensors", "language_model.model.decoder.layers.5.self_attn.k_proj.weight": "model.safetensors", "language_model.model.decoder.layers.5.self_attn.out_proj.bias": "model.safetensors", "language_model.model.decoder.layers.5.self_attn.out_proj.weight": "model.safetensors", "language_model.model.decoder.layers.5.self_attn.q_proj.bias": "model.safetensors", "language_model.model.decoder.layers.5.self_attn.q_proj.weight": "model.safetensors", "language_model.model.decoder.layers.5.self_attn.v_proj.bias": "model.safetensors", "language_model.model.decoder.layers.5.self_attn.v_proj.weight": "model.safetensors", "language_model.model.decoder.layers.5.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.decoder.layers.5.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.encoder.embed_positions.weight": "model.safetensors", "language_model.model.encoder.layernorm_embedding.bias": "model.safetensors", "language_model.model.encoder.layernorm_embedding.weight": "model.safetensors", "language_model.model.encoder.layers.0.fc1.bias": "model.safetensors", "language_model.model.encoder.layers.0.fc1.weight": "model.safetensors", "language_model.model.encoder.layers.0.fc2.bias": "model.safetensors", "language_model.model.encoder.layers.0.fc2.weight": "model.safetensors", "language_model.model.encoder.layers.0.final_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.0.final_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors", "language_model.model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors", "language_model.model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors", "language_model.model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors", "language_model.model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors", "language_model.model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors", "language_model.model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors", "language_model.model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors", "language_model.model.encoder.layers.0.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.0.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.1.fc1.bias": "model.safetensors", "language_model.model.encoder.layers.1.fc1.weight": "model.safetensors", "language_model.model.encoder.layers.1.fc2.bias": "model.safetensors", "language_model.model.encoder.layers.1.fc2.weight": "model.safetensors", "language_model.model.encoder.layers.1.final_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.1.final_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors", "language_model.model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors", "language_model.model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors", "language_model.model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors", "language_model.model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors", "language_model.model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors", "language_model.model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors", "language_model.model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors", "language_model.model.encoder.layers.1.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.1.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.2.fc1.bias": "model.safetensors", "language_model.model.encoder.layers.2.fc1.weight": "model.safetensors", "language_model.model.encoder.layers.2.fc2.bias": "model.safetensors", "language_model.model.encoder.layers.2.fc2.weight": "model.safetensors", "language_model.model.encoder.layers.2.final_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.2.final_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors", "language_model.model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors", "language_model.model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors", "language_model.model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors", "language_model.model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors", "language_model.model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors", "language_model.model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors", "language_model.model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors", "language_model.model.encoder.layers.2.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.2.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.3.fc1.bias": "model.safetensors", "language_model.model.encoder.layers.3.fc1.weight": "model.safetensors", "language_model.model.encoder.layers.3.fc2.bias": "model.safetensors", "language_model.model.encoder.layers.3.fc2.weight": "model.safetensors", "language_model.model.encoder.layers.3.final_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.3.final_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors", "language_model.model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors", "language_model.model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors", "language_model.model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors", "language_model.model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors", "language_model.model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors", "language_model.model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors", "language_model.model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors", "language_model.model.encoder.layers.3.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.3.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.4.fc1.bias": "model.safetensors", "language_model.model.encoder.layers.4.fc1.weight": "model.safetensors", "language_model.model.encoder.layers.4.fc2.bias": "model.safetensors", "language_model.model.encoder.layers.4.fc2.weight": "model.safetensors", "language_model.model.encoder.layers.4.final_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.4.final_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors", "language_model.model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors", "language_model.model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors", "language_model.model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors", "language_model.model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors", "language_model.model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors", "language_model.model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors", "language_model.model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors", "language_model.model.encoder.layers.4.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.4.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.5.fc1.bias": "model.safetensors", "language_model.model.encoder.layers.5.fc1.weight": "model.safetensors", "language_model.model.encoder.layers.5.fc2.bias": "model.safetensors", "language_model.model.encoder.layers.5.fc2.weight": "model.safetensors", "language_model.model.encoder.layers.5.final_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.5.final_layer_norm.weight": "model.safetensors", "language_model.model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors", "language_model.model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors", "language_model.model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors", "language_model.model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors", "language_model.model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors", "language_model.model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors", "language_model.model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors", "language_model.model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors", "language_model.model.encoder.layers.5.self_attn_layer_norm.bias": "model.safetensors", "language_model.model.encoder.layers.5.self_attn_layer_norm.weight": "model.safetensors", "language_model.model.shared.weight": "model.safetensors", "vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.0.0.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.0.0.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.0.0.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.0.0.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.0.0.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.0.0.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.0.0.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.0.0.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.0.0.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.1.0.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.1.0.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.1.0.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.1.0.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.1.0.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.1.0.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.1.0.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.1.0.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.1.0.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.0.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.0.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.0.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.0.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.0.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.0.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.0.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.0.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.0.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.1.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.1.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.1.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.1.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.1.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.1.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.1.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.1.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.1.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.2.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.2.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.2.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.2.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.2.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.2.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.2.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.2.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.2.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.3.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.3.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.3.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.3.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.3.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.3.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.3.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.3.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.3.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.4.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.4.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.4.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.4.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.4.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.4.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.4.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.4.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.4.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.5.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.5.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.5.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.5.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.5.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.5.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.5.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.5.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.5.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.6.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.6.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.6.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.6.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.6.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.6.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.6.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.6.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.6.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.7.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.7.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.7.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.7.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.7.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.7.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.7.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.7.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.7.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.8.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.8.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.2.8.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.8.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.8.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.8.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.8.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.8.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.2.8.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.3.0.channel_block.channel_attn.norm.bias": "model.safetensors", "vision_tower.blocks.3.0.channel_block.channel_attn.norm.weight": "model.safetensors", "vision_tower.blocks.3.0.channel_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.3.0.channel_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.3.0.channel_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.3.0.channel_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.3.0.channel_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.3.0.channel_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.bias": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.weight": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.bias": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.weight": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.ffn.norm.bias": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.ffn.norm.weight": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.bias": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.weight": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.bias": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.weight": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.window_attn.norm.bias": "model.safetensors", "vision_tower.blocks.3.0.spatial_block.window_attn.norm.weight": "model.safetensors", "vision_tower.convs.0.norm.bias": "model.safetensors", "vision_tower.convs.0.norm.weight": "model.safetensors", "vision_tower.convs.0.proj.bias": "model.safetensors", "vision_tower.convs.0.proj.weight": "model.safetensors", "vision_tower.convs.1.norm.bias": "model.safetensors", "vision_tower.convs.1.norm.weight": "model.safetensors", "vision_tower.convs.1.proj.bias": "model.safetensors", "vision_tower.convs.1.proj.weight": "model.safetensors", "vision_tower.convs.2.norm.bias": "model.safetensors", "vision_tower.convs.2.norm.weight": "model.safetensors", "vision_tower.convs.2.proj.bias": "model.safetensors", "vision_tower.convs.2.proj.weight": "model.safetensors", "vision_tower.convs.3.norm.bias": "model.safetensors", "vision_tower.convs.3.norm.weight": "model.safetensors", "vision_tower.convs.3.proj.bias": "model.safetensors", "vision_tower.convs.3.proj.weight": "model.safetensors", "visual_temporal_embed.pos_idx_to_embed": "model.safetensors" } }