{ "architectures": [ "PhiForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 50256, "dtype": "float32", "embd_pdrop": 0.0, "eos_token_id": 50256, "hidden_act": "gelu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 32, "is_decoder": true, "layer_norm_eps": 1e-05, "max_position_embeddings": 512, "model_type": "phi", "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "partial_rotary_factor": 0.5, "qk_layernorm": false, "resid_pdrop": 0.0, "rope_parameters": { "partial_rotary_factor": 0.5, "rope_theta": 10000.0, "rope_type": "default" }, "tie_word_embeddings": false, "transformers_version": "5.16.0.dev0", "use_cache": true, "vocab_size": 50295 }