| { | |
| "architectures": [ | |
| "PhiEncoderModel" | |
| ], | |
| "bos_token_id": 50256, | |
| "eos_token_id": 50256, | |
| "pad_token_id": 50256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "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_scaling": null, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float16", | |
| "use_cache": true, | |
| "vocab_size": 51200 | |
| } | |