{ "_name_or_path": "microsoft/phi-2", "architectures": [ "DribbleForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig", "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM" }, "bos_token_id": 50256, "embd_pdrop": 0.0, "eos_token_id": 50256, "hidden_act": "gelu_new", "hidden_size": 2560, "initializer_range": 0.02, "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, "only_attend_immediate_media": true, "partial_rotary_factor": 0.4, "perceiver_depth": 6, "perceiver_dim": 512, "perceiver_dim_head": 64, "perceiver_ff_mult": 4, "perceiver_heads": 8, "perceiver_num_latents": 256, "perceiver_num_media_embeds": 256, "qk_layernorm": false, "resid_pdrop": 0.1, "rope_scaling": null, "rope_theta": 10000.0, "team_token_id": 0, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.36.2", "use_cache": true, "vocab_size": 51200 }