| {"hidden_act": "gelu", "architectures": ["GPTNeoXForCausalLM"], "bos_token_id": 0, "eos_token_id": 0, "initializer_range": 0.02, "layer_norm_eps": 1e-05, "model_type": "gpt_neox", "hidden_size": 5120, "intermediate_size": 20480, "num_attention_heads": 40, "num_hidden_layers": 40, "max_position_embeddings": 2048, "rotary_pct": 0.5, "rotary_emb_base": 10000, "torch_dtype": "float16", "use_cache": true, "vocab_size": 30080, "num_steps": "global_step301000"} |