{ "architectures": [ "PhiForCausalLM" ], "auto_map": { "AutoConfig": "configuration_phi.PhiConfig", "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM" }, "bias": true, "hidden_act": "gelu", "hidden_size": 2560, "intermediate_size": 10240, "layer_norm_eps": 1e-05, "max_position_embeddings": 2048, "model_type": "phi", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "partial_rotary_factor": 0.4, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.34.0", "use_cache": true, "vocab_size": 51200 }