| { |
| "metadata": { |
| "total_size": 2260800000 |
| }, |
| "weight_map": { |
| "head.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.0.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.pre_ln.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.0.pre_ln.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.1.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.10.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.11.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.12.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.13.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.14.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.15.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.16.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.17.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.18.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.19.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.2.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.20.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.21.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.22.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.23.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.24.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.25.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.26.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.27.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.28.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.29.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.3.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.30.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.31.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.32.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.33.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.34.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.35.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.36.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.37.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.38.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.39.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.4.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.40.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.41.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.42.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.43.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.44.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.45.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.46.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.47.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.48.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.49.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.5.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.50.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.51.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.52.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.53.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.54.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.55.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.56.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.57.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.attention.output.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.58.attention.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.58.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.attention.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.58.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.58.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.58.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.58.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.58.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.58.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.58.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.59.attention.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.attention.output.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.attention.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.attention.time_decay": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.attention.time_first": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.attention.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.attention.time_mix_value": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.attention.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.ln1.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.ln1.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.ln2.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.59.ln2.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.6.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.6.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.60.attention.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.attention.output.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.attention.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.attention.time_decay": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.attention.time_first": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.attention.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.attention.time_mix_value": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.attention.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.ln1.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.ln1.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.ln2.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.60.ln2.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.output.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.time_decay": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.time_first": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.time_mix_value": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.attention.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.ln1.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.ln1.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.ln2.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.61.ln2.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.output.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.time_decay": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.time_first": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.time_mix_value": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.attention.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.ln1.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.ln1.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.ln2.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.62.ln2.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.output.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.time_decay": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.time_first": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.time_mix_value": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.attention.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.ln1.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.ln1.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.ln2.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.63.ln2.weight": "pytorch_model-00002-of-00002.bin", |
| "rwkv.blocks.7.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.7.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.8.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.output.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.time_decay": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.time_first": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.time_mix_value": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.attention.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.ln1.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.ln1.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.ln2.bias": "pytorch_model-00001-of-00002.bin", |
| "rwkv.blocks.9.ln2.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.embeddings.weight": "pytorch_model-00001-of-00002.bin", |
| "rwkv.ln_out.bias": "pytorch_model-00002-of-00002.bin", |
| "rwkv.ln_out.weight": "pytorch_model-00002-of-00002.bin" |
| } |
| } |
|
|
