diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" new file mode 100644--- /dev/null +++ "b/model.safetensors.index.json" @@ -0,0 +1,1394 @@ +{ + "metadata": { + "total_size": 14950488064 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.image_tower.image_tower.embeddings.class_embedding": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.post_layernorm.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.post_layernorm.weight": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.pre_layrnorm.bias": "model-00003-of-00004.safetensors", + "model.image_tower.image_tower.pre_layrnorm.weight": "model-00003-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.k_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.k_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.q_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.q_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.residual.dense.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.residual.dense.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.residual.layernorm.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.residual.layernorm.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.v_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.crossattention.v_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.mlp.0.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.mlp.0.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.residual.dense.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.residual.dense.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.residual.layernorm.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.residual.layernorm.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.k_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.k_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.q_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.q_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.residual.dense.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.residual.dense.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.residual.layernorm.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.residual.layernorm.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.v_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.layers.0.selfattention.v_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.memory_tokens": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.proj.0.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.proj.0.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.projector.read_memory_emb": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.k_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.k_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.q_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.q_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.residual.dense.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.residual.dense.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.residual.layernorm.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.residual.layernorm.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.v_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.crossattention.v_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.k_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.k_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.q_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.q_proj.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.residual.dense.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.residual.dense.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.residual.layernorm.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.residual.layernorm.weight": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.v_proj.bias": "model-00003-of-00004.safetensors", + "model.mm_projector.retrieval.layers.0.selfattention.v_proj.weight": "model-00003-of-00004.safetensors", + "model.norm.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.embeddings.class_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.0.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.1.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.10.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.11.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.12.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.13.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.14.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.15.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.16.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.17.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.18.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.19.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.2.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.20.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.21.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.22.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.23.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.3.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.4.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.5.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.6.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.7.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.8.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_attn.out_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_attn.out_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_embedding": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_layer_norm1.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.encoder.layers.9.temporal_layer_norm1.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.post_layernorm.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.post_layernorm.weight": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.pre_layrnorm.bias": "model-00003-of-00004.safetensors", + "model.video_tower.video_tower.pre_layrnorm.weight": "model-00003-of-00004.safetensors" + } +}