| { | |
| "metadata": { | |
| "total_size": 16966988452 | |
| }, | |
| "weight_map": { | |
| "encoder.out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.out_mid.bias": "model-00009-of-00009.safetensors", | |
| "encoder.out_mid.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.1.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.10.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.2.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.3.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.4.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.5.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.6.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.7.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.8.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.attn.fn.rel_pos_emb.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.attn.fn.to_kv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.attn.fn.to_out.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.attn.fn.to_out.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.attn.fn.to_q.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.attn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.attn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.2.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.2.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.4.conv.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.5.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.5.num_batches_tracked": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.5.running_mean": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.5.running_var": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.5.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.7.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.conv.net.7.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff1.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff1.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff1.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff1.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff1.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff1.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff2.fn.fn.net.0.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff2.fn.fn.net.0.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff2.fn.fn.net.3.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff2.fn.fn.net.3.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff2.fn.norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.ff2.fn.norm.weight": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.post_norm.bias": "model-00009-of-00009.safetensors", | |
| "encoder.rnn_tr.9.post_norm.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.embed_tokens.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.mlp.up_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", | |
| "language_model.model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.20.mlp.down_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.20.mlp.up_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.mlp.down_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", | |
| "language_model.model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.24.mlp.down_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.24.mlp.up_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.mlp.down_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.mlp.up_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.mlp.down_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.mlp.up_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", | |
| "language_model.model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.29.mlp.down_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.29.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.29.mlp.up_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", | |
| "language_model.model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.30.mlp.down_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.30.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.30.mlp.up_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.mlp.down_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.mlp.up_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.mlp.down_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.mlp.up_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.32.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.mlp.down_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", | |
| "language_model.model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.34.mlp.down_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.34.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.34.mlp.up_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.mlp.down_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.mlp.up_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.input_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.mlp.down_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.mlp.up_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.36.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.input_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.mlp.down_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.mlp.up_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.37.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.mlp.down_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.mlp.up_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.38.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", | |
| "language_model.model.layers.39.input_layernorm.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.39.mlp.down_proj.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.39.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.39.mlp.up_proj.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.39.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.39.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.39.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.39.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.39.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", | |
| "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", | |
| "language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", | |
| "language_model.model.norm.weight": "model-00009-of-00009.safetensors", | |
| "projector.linear.bias": "model-00009-of-00009.safetensors", | |
| "projector.linear.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.attention.key.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.attention.key.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.attention.query.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.attention.query.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.attention.value.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.attention.value.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.output.LayerNorm.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.output.LayerNorm.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.output.dense.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.attention.output.dense.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.attention.key.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.attention.key.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.attention.query.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.attention.query.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.attention.value.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.attention.value.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.output.dense.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.crossattention.output.dense.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.intermediate_query.dense.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.intermediate_query.dense.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.output_query.LayerNorm.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.output_query.LayerNorm.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.output_query.dense.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.0.output_query.dense.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.attention.key.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.attention.key.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.attention.query.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.attention.query.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.attention.value.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.attention.value.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.output.LayerNorm.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.output.LayerNorm.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.output.dense.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.attention.output.dense.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.attention.key.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.attention.key.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.attention.query.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.attention.query.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.attention.value.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.attention.value.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.output.LayerNorm.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.output.LayerNorm.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.output.dense.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.crossattention.output.dense.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.intermediate_query.dense.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.intermediate_query.dense.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.output_query.LayerNorm.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.output_query.LayerNorm.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.output_query.dense.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.encoder.layer.1.output_query.dense.weight": "model-00009-of-00009.safetensors", | |
| "projector.qformer.layernorm.bias": "model-00009-of-00009.safetensors", | |
| "projector.qformer.layernorm.weight": "model-00009-of-00009.safetensors", | |
| "projector.query": "model-00009-of-00009.safetensors" | |
| } | |
| } | |