| { | |
| "_from_model_config": true, | |
| "architectures": [ | |
| "BaichuanForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_baichuan.BaichuanConfig", | |
| "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM" | |
| }, | |
| "sakura_name": "Sakura-13B-LNovel", | |
| "sakura_version": "0.8", | |
| "sakura_quant": "3bit", | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13696, | |
| "model_max_length": 4096, | |
| "model_type": "baichuan", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "BaichuanTokenizer", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.33.2", | |
| "use_cache": false, | |
| "vocab_size": 125696, | |
| "z_loss_weight": 0 | |
| } | |