| { | |
| "_name_or_path": "/data/nvme3/trained_ckpt/saved_models_3.5M/checkpoint-11270", | |
| "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_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": "float16", | |
| "transformers_version": "4.30.2", | |
| "use_cache": false, | |
| "vocab_size": 64000 | |
| } | |