{ "_name_or_path": "01-ai/Yi-6B-200K", "architectures": [ "YiForCausalLM" ], "auto_map": { "AutoConfig": "01-ai/Yi-6B-200K--configuration_yi.YiConfig", "AutoModel": "01-ai/Yi-6B-200K--modeling_yi.YiModel", "AutoModelForCausalLM": "01-ai/Yi-6B-200K--modeling_yi.YiForCausalLM" }, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 200000, "model_type": "Yi", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 4, "pad_token_id": 0, "rms_norm_eps": 1e-05, "rope_theta": 5000000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.36.0.dev0", "use_cache": true, "vocab_size": 64000 }