| { |
| "_name_or_path": "output/sft", |
| "architectures": [ |
| "LlamaModelForScore" |
| ], |
| "bias": false, |
| "bos_token_id": 1, |
| "do_normalize": false, |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "max_position_embeddings": 2048, |
| "max_sequence_length": 2048, |
| "mean": [ |
| 7.4375 |
| ], |
| "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, |
| "score_dim": 1, |
| "score_type": "reward", |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.31.0", |
| "use_cache": true, |
| "var": [ |
| 82.5 |
| ], |
| "vocab_size": 32001 |
| } |
|
|
