| { | |
| "metadata": { | |
| "total_size": 21757968706 | |
| }, | |
| "weight_map": { | |
| "adapter.fc1.bias": "model-00002-of-00005.safetensors", | |
| "adapter.fc1.weight": "model-00002-of-00005.safetensors", | |
| "adapter.fc2.bias": "model-00002-of-00005.safetensors", | |
| "adapter.fc2.weight": "model-00002-of-00005.safetensors", | |
| "adapter.ln1.bias": "model-00002-of-00005.safetensors", | |
| "adapter.ln1.weight": "model-00002-of-00005.safetensors", | |
| "adapter.ln2.bias": "model-00002-of-00005.safetensors", | |
| "adapter.ln2.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.contact_head.regression.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.contact_head.regression.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.embeddings.position_embeddings.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.embeddings.word_embeddings.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.emb_layer_norm_after.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.emb_layer_norm_after.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.0.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.1.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.10.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.11.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.12.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.13.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.14.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.15.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.16.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.17.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.18.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.19.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.2.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.20.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.21.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.22.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.23.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.24.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.25.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.26.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.27.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.28.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.29.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.3.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.30.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.31.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.self.key.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.self.key.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.self.query.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.self.query.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.self.rotary_embeddings.inv_freq": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.self.value.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.attention.self.value.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.intermediate.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.intermediate.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.32.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.self.key.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.self.key.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.self.query.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.self.query.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.self.rotary_embeddings.inv_freq": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.self.value.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.attention.self.value.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.intermediate.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.intermediate.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.33.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.self.key.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.self.key.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.self.query.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.self.query.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.self.rotary_embeddings.inv_freq": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.self.value.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.attention.self.value.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.intermediate.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.intermediate.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.34.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.LayerNorm.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.LayerNorm.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.self.key.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.self.key.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.self.query.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.self.query.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.self.rotary_embeddings.inv_freq": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.self.value.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.attention.self.value.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.intermediate.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.intermediate.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.output.dense.bias": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.35.output.dense.weight": "model-00002-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.4.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.5.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.6.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.7.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.8.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.LayerNorm.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.LayerNorm.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.self.key.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.self.key.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.self.query.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.self.query.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.self.rotary_embeddings.inv_freq": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.self.value.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.attention.self.value.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.output.dense.bias": "model-00001-of-00005.safetensors", | |
| "esm_encoder.encoder.layer.9.output.dense.weight": "model-00001-of-00005.safetensors", | |
| "llama_decoder.lm_head.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.embed_tokens.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "llama_decoder.model.norm.weight": "model-00005-of-00005.safetensors" | |
| } | |
| } | |