{ "_from_model_config": true, "architectures": [ "BaichuanForCausalLM" ], "auto_map": { "AutoConfig": "configuration_baichuan.BaichuanConfig", "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM" }, "tokenizer_class": "BaichuanTokenizer", "bos_token_id": 1, "eos_token_id": 2, "gradient_checkpointing": false, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13696, "model_max_length": 8192, "model_type": "baichuan", "num_attention_heads": 40, "num_hidden_layers": 40, "pad_token_id": 0, "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.29.2", "use_cache": true, "vocab_size": 125696 }