{ "_name_or_path": "microsoft/phi-2", "architectures": [ "PhiForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 50256, "early_stopping": null, "embd_pdrop": 0.0, "eos_token_id": 50256, "hidden_act": "gelu_new", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 2560, "layer_norm_eps": 1e-05, "max_position_embeddings": 2048, "model_type": "phi", "num_attention_heads": 32, "num_beams": null, "num_hidden_layers": 32, "num_key_value_heads": 32, "partial_rotary_factor": 0.4, "qk_layernorm": false, "resid_pdrop": 0.1, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "use_cache": true, "vocab_size": 51200 }