{ "_name_or_path": "/pretrained/huggingface/hub/models--phi-3-mini-4k-instruct-awq-4bit", "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_phi3.Phi3Config", "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "quantization_config": { "backend": "autoawq", "bits": 4, "do_fuse": false, "exllama_config": null, "fuse_max_seq_len": null, "group_size": 128, "modules_to_fuse": null, "modules_to_not_convert": null, "quant_method": "awq", "version": "gemm", "zero_point": true }, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 2047, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.41.2", "use_cache": true, "vocab_size": 32064 }