| { | |
| "metadata": { | |
| "total_size": 1465.361213684082 | |
| }, | |
| "weight_map": { | |
| "x_embedder.proj.weight": "pytorch_model-00001.bin", | |
| "x_embedder.proj.bias": "pytorch_model-00001.bin", | |
| "t_embedder.mlp.0.weight": "pytorch_model-00001.bin", | |
| "t_embedder.mlp.0.bias": "pytorch_model-00001.bin", | |
| "t_embedder.mlp.2.weight": "pytorch_model-00001.bin", | |
| "t_embedder.mlp.2.bias": "pytorch_model-00001.bin", | |
| "t_block.1.weight": "pytorch_model-00001.bin", | |
| "t_block.1.bias": "pytorch_model-00001.bin", | |
| "t_block_temp.1.weight": "pytorch_model-00001.bin", | |
| "t_block_temp.1.bias": "pytorch_model-00001.bin", | |
| "y_embedder.y_embedding": "pytorch_model-00001.bin", | |
| "y_embedder.y_proj.fc1.weight": "pytorch_model-00001.bin", | |
| "y_embedder.y_proj.fc1.bias": "pytorch_model-00001.bin", | |
| "y_embedder.y_proj.fc2.weight": "pytorch_model-00001.bin", | |
| "y_embedder.y_proj.fc2.bias": "pytorch_model-00001.bin", | |
| "rope.freqs": "pytorch_model-00001.bin", | |
| "blocks.0.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.0.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.0.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.0.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.0.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.0.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.0.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.0.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.0.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.0.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.0.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.0.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.0.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.0.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.0.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.0.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.0.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.0.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.0.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.0.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.0.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.0.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.0.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.0.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.1.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.1.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.1.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.1.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.1.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.1.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.1.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.1.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.1.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.1.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.1.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.1.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.1.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.1.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.1.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.1.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.1.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.1.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.1.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.1.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.1.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.1.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.1.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.1.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.2.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.2.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.2.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.2.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.2.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.2.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.2.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.2.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.2.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.2.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.2.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.2.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.2.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.2.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.2.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.2.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.2.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.2.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.2.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.2.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.2.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.2.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.2.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.2.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.3.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.3.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.3.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.3.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.3.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.3.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.3.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.3.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.3.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.3.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.3.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.3.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.3.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.3.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.3.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.3.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.3.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.3.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.3.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.3.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.3.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.3.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.3.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.3.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.4.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.4.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.4.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.4.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.4.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.4.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.4.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.4.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.4.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.4.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.4.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.4.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.4.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.4.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.4.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.4.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.4.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.4.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.4.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.4.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.4.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.4.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.4.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.4.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.5.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.5.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.5.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.5.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.5.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.5.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.5.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.5.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.5.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.5.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.5.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.5.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.5.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.5.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.5.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.5.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.5.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.5.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.5.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.5.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.5.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.5.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.5.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.5.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.6.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.6.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.6.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.6.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.6.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.6.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.6.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.6.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.6.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.6.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.6.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.6.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.6.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.6.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.6.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.6.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.6.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.6.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.6.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.6.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.6.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.6.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.6.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.6.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.7.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.7.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.7.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.7.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.7.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.7.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.7.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.7.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.7.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.7.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.7.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.7.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.7.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.7.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.7.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.7.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.7.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.7.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.7.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.7.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.7.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.7.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.7.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.7.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.8.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.8.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.8.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.8.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.8.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.8.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.8.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.8.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.8.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.8.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.8.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.8.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.8.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.8.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.8.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.8.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.8.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.8.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.8.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.8.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.8.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.8.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.8.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.8.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.9.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.9.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.9.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.9.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.9.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.9.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.9.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.9.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.9.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.9.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.9.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.9.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.9.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.9.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.9.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.9.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.9.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.9.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.9.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.9.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.9.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.9.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.9.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.9.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.10.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.10.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.10.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.10.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.10.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.10.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.10.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.10.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.10.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.10.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.10.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.10.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.10.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.10.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.10.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.10.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.10.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.10.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.10.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.10.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.10.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.10.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.10.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.10.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.11.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.11.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.11.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.11.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.11.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.11.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.11.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.11.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.11.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.11.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.11.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.11.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.11.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.11.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.11.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.11.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.11.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.11.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.11.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.11.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.11.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.11.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.11.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.11.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.12.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.12.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.12.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.12.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.12.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.12.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.12.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.12.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.12.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.12.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.12.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.12.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.12.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.12.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.12.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.12.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.12.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.12.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.12.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.12.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.12.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.12.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.12.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.12.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.13.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.13.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.13.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.13.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.13.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.13.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.13.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.13.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.13.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.13.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.13.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.13.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.13.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.13.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.13.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.13.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.13.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.13.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.13.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.13.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.13.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.13.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.13.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.13.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.14.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.14.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.14.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.14.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.14.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.14.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.14.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.14.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.14.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.14.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.14.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.14.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.14.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.14.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.14.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.14.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.14.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.14.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.14.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.14.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.14.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.14.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.14.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.14.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.15.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.15.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.15.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.15.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.15.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.15.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.15.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.15.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.15.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.15.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.15.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.15.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.15.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.15.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.15.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.15.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.15.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.15.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.15.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.15.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.15.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.15.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.15.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.15.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.16.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.16.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.16.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.16.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.16.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.16.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.16.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.16.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.16.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.16.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.16.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.16.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.16.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.16.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.16.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.16.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.16.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.16.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.16.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.16.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.16.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.16.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.16.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.16.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.17.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.17.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.17.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.17.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.17.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.17.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.17.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.17.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.17.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.17.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.17.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.17.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.17.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.17.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.17.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.17.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.17.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.17.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.17.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.17.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.17.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.17.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.17.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.17.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.18.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.18.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.18.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.18.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.18.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.18.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.18.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.18.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.18.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.18.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.18.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.18.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.18.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.18.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.18.mlp.fc1.weight": "pytorch_model-00001.bin", | |
| "blocks.18.mlp.fc1.bias": "pytorch_model-00001.bin", | |
| "blocks.18.mlp.fc2.weight": "pytorch_model-00001.bin", | |
| "blocks.18.mlp.fc2.bias": "pytorch_model-00001.bin", | |
| "blocks.18.attn_temp.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.18.attn_temp.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.18.attn_temp.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.18.attn_temp.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.18.attn_temp.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.18.attn_temp.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.19.scale_shift_table": "pytorch_model-00001.bin", | |
| "blocks.19.scale_shift_table_temporal": "pytorch_model-00001.bin", | |
| "blocks.19.attn.qkv.weight": "pytorch_model-00001.bin", | |
| "blocks.19.attn.qkv.bias": "pytorch_model-00001.bin", | |
| "blocks.19.attn.q_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.19.attn.k_norm.weight": "pytorch_model-00001.bin", | |
| "blocks.19.attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.19.attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.19.cross_attn.q_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.19.cross_attn.q_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.19.cross_attn.kv_linear.weight": "pytorch_model-00001.bin", | |
| "blocks.19.cross_attn.kv_linear.bias": "pytorch_model-00001.bin", | |
| "blocks.19.cross_attn.proj.weight": "pytorch_model-00001.bin", | |
| "blocks.19.cross_attn.proj.bias": "pytorch_model-00001.bin", | |
| "blocks.19.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.19.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.19.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.19.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.19.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.19.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.19.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.19.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.19.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.19.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.20.scale_shift_table": "pytorch_model-00002.bin", | |
| "blocks.20.scale_shift_table_temporal": "pytorch_model-00002.bin", | |
| "blocks.20.attn.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.20.attn.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.20.attn.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.20.attn.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.20.attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.20.attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.20.cross_attn.q_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.20.cross_attn.q_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.20.cross_attn.kv_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.20.cross_attn.kv_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.20.cross_attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.20.cross_attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.20.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.20.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.20.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.20.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.20.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.20.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.20.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.20.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.20.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.20.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.21.scale_shift_table": "pytorch_model-00002.bin", | |
| "blocks.21.scale_shift_table_temporal": "pytorch_model-00002.bin", | |
| "blocks.21.attn.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.21.attn.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.21.attn.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.21.attn.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.21.attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.21.attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.21.cross_attn.q_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.21.cross_attn.q_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.21.cross_attn.kv_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.21.cross_attn.kv_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.21.cross_attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.21.cross_attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.21.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.21.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.21.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.21.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.21.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.21.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.21.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.21.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.21.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.21.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.22.scale_shift_table": "pytorch_model-00002.bin", | |
| "blocks.22.scale_shift_table_temporal": "pytorch_model-00002.bin", | |
| "blocks.22.attn.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.22.attn.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.22.attn.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.22.attn.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.22.attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.22.attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.22.cross_attn.q_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.22.cross_attn.q_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.22.cross_attn.kv_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.22.cross_attn.kv_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.22.cross_attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.22.cross_attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.22.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.22.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.22.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.22.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.22.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.22.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.22.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.22.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.22.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.22.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.23.scale_shift_table": "pytorch_model-00002.bin", | |
| "blocks.23.scale_shift_table_temporal": "pytorch_model-00002.bin", | |
| "blocks.23.attn.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.23.attn.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.23.attn.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.23.attn.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.23.attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.23.attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.23.cross_attn.q_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.23.cross_attn.q_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.23.cross_attn.kv_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.23.cross_attn.kv_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.23.cross_attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.23.cross_attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.23.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.23.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.23.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.23.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.23.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.23.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.23.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.23.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.23.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.23.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.24.scale_shift_table": "pytorch_model-00002.bin", | |
| "blocks.24.scale_shift_table_temporal": "pytorch_model-00002.bin", | |
| "blocks.24.attn.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.24.attn.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.24.attn.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.24.attn.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.24.attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.24.attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.24.cross_attn.q_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.24.cross_attn.q_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.24.cross_attn.kv_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.24.cross_attn.kv_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.24.cross_attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.24.cross_attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.24.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.24.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.24.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.24.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.24.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.24.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.24.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.24.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.24.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.24.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.25.scale_shift_table": "pytorch_model-00002.bin", | |
| "blocks.25.scale_shift_table_temporal": "pytorch_model-00002.bin", | |
| "blocks.25.attn.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.25.attn.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.25.attn.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.25.attn.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.25.attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.25.attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.25.cross_attn.q_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.25.cross_attn.q_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.25.cross_attn.kv_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.25.cross_attn.kv_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.25.cross_attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.25.cross_attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.25.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.25.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.25.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.25.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.25.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.25.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.25.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.25.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.25.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.25.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.26.scale_shift_table": "pytorch_model-00002.bin", | |
| "blocks.26.scale_shift_table_temporal": "pytorch_model-00002.bin", | |
| "blocks.26.attn.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.26.attn.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.26.attn.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.26.attn.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.26.attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.26.attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.26.cross_attn.q_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.26.cross_attn.q_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.26.cross_attn.kv_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.26.cross_attn.kv_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.26.cross_attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.26.cross_attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.26.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.26.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.26.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.26.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.26.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.26.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.26.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.26.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.26.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.26.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.27.scale_shift_table": "pytorch_model-00002.bin", | |
| "blocks.27.scale_shift_table_temporal": "pytorch_model-00002.bin", | |
| "blocks.27.attn.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.27.attn.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.27.attn.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.27.attn.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.27.attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.27.attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.27.cross_attn.q_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.27.cross_attn.q_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.27.cross_attn.kv_linear.weight": "pytorch_model-00002.bin", | |
| "blocks.27.cross_attn.kv_linear.bias": "pytorch_model-00002.bin", | |
| "blocks.27.cross_attn.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.27.cross_attn.proj.bias": "pytorch_model-00002.bin", | |
| "blocks.27.mlp.fc1.weight": "pytorch_model-00002.bin", | |
| "blocks.27.mlp.fc1.bias": "pytorch_model-00002.bin", | |
| "blocks.27.mlp.fc2.weight": "pytorch_model-00002.bin", | |
| "blocks.27.mlp.fc2.bias": "pytorch_model-00002.bin", | |
| "blocks.27.attn_temp.qkv.weight": "pytorch_model-00002.bin", | |
| "blocks.27.attn_temp.qkv.bias": "pytorch_model-00002.bin", | |
| "blocks.27.attn_temp.q_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.27.attn_temp.k_norm.weight": "pytorch_model-00002.bin", | |
| "blocks.27.attn_temp.proj.weight": "pytorch_model-00002.bin", | |
| "blocks.27.attn_temp.proj.bias": "pytorch_model-00002.bin", | |
| "final_layer.scale_shift_table": "pytorch_model-00002.bin", | |
| "final_layer.linear.weight": "pytorch_model-00002.bin", | |
| "final_layer.linear.bias": "pytorch_model-00002.bin", | |
| "csize_embedder.mlp.0.weight": "pytorch_model-00002.bin", | |
| "csize_embedder.mlp.0.bias": "pytorch_model-00002.bin", | |
| "csize_embedder.mlp.2.weight": "pytorch_model-00002.bin", | |
| "csize_embedder.mlp.2.bias": "pytorch_model-00002.bin", | |
| "ar_embedder.mlp.0.weight": "pytorch_model-00002.bin", | |
| "ar_embedder.mlp.0.bias": "pytorch_model-00002.bin", | |
| "ar_embedder.mlp.2.weight": "pytorch_model-00002.bin", | |
| "ar_embedder.mlp.2.bias": "pytorch_model-00002.bin", | |
| "fl_embedder.mlp.0.weight": "pytorch_model-00002.bin", | |
| "fl_embedder.mlp.0.bias": "pytorch_model-00002.bin", | |
| "fl_embedder.mlp.2.weight": "pytorch_model-00002.bin", | |
| "fl_embedder.mlp.2.bias": "pytorch_model-00002.bin", | |
| "fps_embedder.mlp.0.weight": "pytorch_model-00002.bin", | |
| "fps_embedder.mlp.0.bias": "pytorch_model-00002.bin", | |
| "fps_embedder.mlp.2.weight": "pytorch_model-00002.bin", | |
| "fps_embedder.mlp.2.bias": "pytorch_model-00002.bin" | |
| } | |
| } | |