{ "_name_or_path": "/mnt/workspace/.cache/modelscope/01ai/Yi-1___5-6B-Chat", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "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": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 4, "pad_token_id": 0, "pretraining_tp": 1, "quantization_config": { "bits": 4, "damp_percent": 0.1, "desc_act": false, "group_size": 128, "modules_in_block_to_quantize": null, "quant_method": "gptq", "sym": true, "true_sequential": true }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.39.3", "use_cache": false, "vocab_size": 64000 }