| { | |
| "_from_model_config": true, | |
| "_name_or_path": "/data1/cjh/models/tonggu-sft-stage1-400wa2m3eph-RAT", | |
| "architectures": [ | |
| "BaichuanForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_baichuan.BaichuanConfig", | |
| "AutoModel": "modeling_baichuan.BaichuanForCausalLM", | |
| "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, | |
| "rms_norm_eps": 1e-06, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.34.1", | |
| "use_cache": false, | |
| "vocab_size": 125696, | |
| "z_loss_weight": 0 | |
| } | |