{ "_name_or_path": "/mnt/cfs1/zhangxu/xverse_ckpts/xland/xverse2-13b-fanyule847491-1204_xland-1226/pretrain_MP1/iter_0000846/mp_rank_00", "architectures": [ "XverseForCausalLM" ], "auto_map": { "AutoConfig": "configuration_xverse.XverseConfig", "AutoModelForCausalLM": "modeling_xverse.XverseForCausalLM" }, "bos_token_id": 2, "eos_token_id": 3, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 8192, "max_tokenizer_truncation": 6144, "model_type": "xverse", "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "pad_token_id": 1, "quantization_config": { "bits": 8, "damp_percent": 0.01, "desc_act": true, "group_size": 128, "is_marlin_format": false, "model_file_base_name": "gptq_model-8bit-128g", "model_name_or_path": "/mnt/llm_dataset/xverse_models/gptq/XVERSE-13B-Chat-GPTQ-Int8", "quant_method": "gptq", "static_groups": true, "sym": true, "true_sequential": true }, "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.38.2", "use_cache": true, "vocab_size": 100534 }