| { | |
| "_name_or_path": "NRJ-350", | |
| "activation": "softmax", | |
| "alpha": 0.1, | |
| "architectures": [ | |
| "BertEnergyModelForMaskedLM" | |
| ], | |
| "auto_map": { | |
| "AutoModel": "mlm.BertEnergyModelForMaskedLM" | |
| }, | |
| "beta": 0.125, | |
| "bias": true, | |
| "block_size": 512, | |
| "compile": false, | |
| "dropout": 0.1, | |
| "embedding_dim": 768, | |
| "forward_memories": 3072, | |
| "layer_norm": 1e-12, | |
| "model_type": "bert_energy", | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "pad_idx": null, | |
| "positional": true, | |
| "share_layers": false, | |
| "tie_weights": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.0", | |
| "vocabulary_size": 30000 | |
| } | |