| { | |
| "metadata": { | |
| "total_size": 6446374976 | |
| }, | |
| "weight_map": { | |
| "bert.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.mlp.gate_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.24.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.24.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.25.attention.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.self.key.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.self.key.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.self.query.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.self.query.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.self.value.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.attention.self.value.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.mlp.down_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.mlp.gate_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.mlp.up_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.self.key.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.self.key.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.self.query.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.self.query.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.self.value.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.attention.self.value.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.mlp.down_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.mlp.gate_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.mlp.up_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.self.key.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.self.key.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.self.query.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.self.query.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.self.value.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.attention.self.value.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.mlp.down_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.mlp.gate_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.mlp.up_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.self.key.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.self.key.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.self.query.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.self.query.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.self.value.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.attention.self.value.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.mlp.down_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.mlp.gate_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.mlp.up_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.self.key.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.self.key.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.self.query.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.self.query.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.self.value.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.attention.self.value.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.mlp.down_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.mlp.gate_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.mlp.up_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.3.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.30.attention.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.self.key.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.self.key.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.self.query.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.self.query.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.self.value.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.attention.self.value.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.mlp.down_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.mlp.gate_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.mlp.up_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.self.key.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.self.key.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.self.query.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.self.query.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.self.value.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.attention.self.value.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.mlp.down_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.mlp.gate_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.mlp.up_proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.layer.4.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.self.key.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.self.key.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.self.query.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.self.query.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.self.value.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.attention.self.value.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.ln.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.ln.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.layer.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "bert.encoder.ln.bias": "pytorch_model-00002-of-00002.bin", | |
| "bert.encoder.ln.weight": "pytorch_model-00002-of-00002.bin", | |
| "cls.predictions.bias": "pytorch_model-00002-of-00002.bin", | |
| "cls.predictions.decoder.bias": "pytorch_model-00002-of-00002.bin", | |
| "cls.predictions.decoder.weight": "pytorch_model-00001-of-00002.bin", | |
| "cls.predictions.transform.LayerNorm.bias": "pytorch_model-00002-of-00002.bin", | |
| "cls.predictions.transform.LayerNorm.weight": "pytorch_model-00002-of-00002.bin", | |
| "cls.predictions.transform.dense.bias": "pytorch_model-00002-of-00002.bin", | |
| "cls.predictions.transform.dense.weight": "pytorch_model-00002-of-00002.bin" | |
| } | |
| } | |