| { | |
| "_name_or_path": "yyqoni/rlhflow-llama-3-sft-8b-v2-token-rm-700k", | |
| "architectures": [ | |
| "LlamaForSequenceClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128009, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "max_position_embeddings": 8192, | |
| "mean": -2.582430362701416, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "normalize_reward": false, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "std": 3.0203094482421875, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.47.1", | |
| "use_cache": false, | |
| "vocab_size": 128256 | |
| } | |