{ "_from_model_config": true, "_name_or_path": "HuatuoGPT2-7B", "architectures": [ "BaichuanForCausalLM" ], "auto_map": { "AutoConfig": "configuration_baichuan.BaichuanConfig", "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM" }, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "model_max_length": 4096, "model_type": "baichuan", "num_attention_heads": 32, "num_hidden_layers": 32, "pad_token_id": 0, "quantization_config": { "batch_size": 1, "bits": 8, "block_name_to_quantize": "model.layers", "damp_percent": 0.1, "desc_act": false, "disable_exllama": false, "group_size": 128, "model_seqlen": 4096, "module_name_preceding_first_block": [ "model.embed_tokens" ], "pad_token_id": null, "quant_method": "gptq", "sym": true, "tokenizer": null, "true_sequential": true, "use_cuda_fp16": true }, "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "tokenizer_class": "BaichuanTokenizer", "torch_dtype": "float16", "transformers_version": "4.33.1", "use_cache": true, "vocab_size": 125696, "z_loss_weight": 0 }