config.json
| 1 | { |
| 2 | "_name_or_path": "microsoft/phi-4", |
| 3 | "architectures": [ |
| 4 | "Phi3ForCausalLM" |
| 5 | ], |
| 6 | "attention_bias": false, |
| 7 | "attention_dropout": 0.0, |
| 8 | "bos_token_id": 100257, |
| 9 | "embd_pdrop": 0.0, |
| 10 | "eos_token_id": 100265, |
| 11 | "hidden_act": "silu", |
| 12 | "hidden_size": 5120, |
| 13 | "initializer_range": 0.02, |
| 14 | "intermediate_size": 17920, |
| 15 | "max_position_embeddings": 16384, |
| 16 | "model_type": "phi3", |
| 17 | "num_attention_heads": 40, |
| 18 | "num_hidden_layers": 40, |
| 19 | "num_key_value_heads": 10, |
| 20 | "original_max_position_embeddings": 16384, |
| 21 | "pad_token_id": 100349, |
| 22 | "resid_pdrop": 0.0, |
| 23 | "rms_norm_eps": 1e-05, |
| 24 | "rope_scaling": null, |
| 25 | "rope_theta": 250000, |
| 26 | "sliding_window": null, |
| 27 | "tie_word_embeddings": false, |
| 28 | "torch_dtype": "bfloat16", |
| 29 | "transformers_version": "4.47.0", |
| 30 | "use_cache": true, |
| 31 | "vocab_size": 100352 |
| 32 | } |
| 33 | |