{ "_name_or_path": "/home/nz/rm-ckpts/ckpt-410m/", "architectures": [ "LLMForSequenceRegression" ], "attention_bias": true, "attention_dropout": 0.0, "bos_token_id": 0, "classifier_dropout": 0.1, "eos_token_id": 0, "hidden_act": "gelu", "hidden_dropout": 0.0, "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-05, "max_position_embeddings": 2048, "mean": 0.7761991620063782, "model_type": "gpt_neox", "normalize_reward": false, "num_attention_heads": 16, "num_hidden_layers": 24, "pad_token_id": 0, "rope_scaling": null, "rotary_emb_base": 10000, "rotary_pct": 0.25, "std": 1.0839786529541016, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.37.0", "use_cache": true, "use_parallel_residual": true, "vocab_size": 50304 }