| { | |
| "_name_or_path": "/home/juntao/Projects/roo-dev-djt/rebuttals/outputs/score_lm/alpaca-7b_unfreeze_original_1119", | |
| "architectures": [ | |
| "LlamaForScoreLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "do_normalize": false, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 2048, | |
| "mean": [ | |
| -0.13911497592926025 | |
| ], | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "momentum": 0.9, | |
| "normalizer_type": "ExponentialMovingAverage", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 32000, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "score_bias": true, | |
| "score_dim": 1, | |
| "score_type": "reward", | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.2", | |
| "use_cache": true, | |
| "var": [ | |
| 5.410205364227295 | |
| ], | |
| "vocab_size": 32001 | |
| } | |