{ "_name_or_path": "/home/xuehy/WORKSPACE/safe-rlhf/../OpenRLHF/ckpt/TinyLlama-1.1b-sft-model-ocra-200k", "architectures": [ "LlamaForScore" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "do_normalize": false, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 2048, "mean": [ -0.050561681389808655 ], "model_type": "llama", "momentum": 0.9, "normalizer_type": "ExponentialMovingAverage", "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "pad_token_id": 2, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "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": "4.37.2", "use_cache": true, "var": [ 3.775546073913574 ], "vocab_size": 32000 }