| { | |
| "_from_model_config": true, | |
| "architectures": [ | |
| "BaichuanForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_baichuan.BaichuanConfig", | |
| "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM" | |
| }, | |
| "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": 4096, | |
| "model_type": "baichuan", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": true, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.29.2", | |
| "use_cache": true, | |
| "vocab_size": 125696 | |
| } | |