{ "_flash_attn_2_enabled": true, "architectures": [ "PhiForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_phi2_clex.CLEXPhiConfig", "AutoModelForCausalLM": "modeling_phi2_clex.PhiForCausalLM" }, "bos_token_id": null, "embd_pdrop": 0.0, "eos_token_id": null, "hidden_act": "gelu_new", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 10240, "layer_norm_eps": 1e-05, "log_scale": false, "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, "qk_layernorm": false, "resid_pdrop": 0.1, "rope_scaling": { "factor": 1, "max_factor": 64, "param_factor": 1, "time_dt": 0.01, "type": "clex", "act": "tanh" }, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.36.2", "use_cache": true, "vocab_size": 51200 }