| { | |
| "architectures": [ | |
| "PhiForCausalLM" | |
| ], | |
| "attention_dropout": 0.2, | |
| "attn_pdrop": 0.2, | |
| "bos_token_id": 126, | |
| "embd_pdrop": 0.2, | |
| "eos_token_id": 127, | |
| "hidden_act": "gelu_new", | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 256, | |
| "model_type": "phi", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "num_key_value_heads": 12, | |
| "partial_rotary_factor": 0.5, | |
| "qk_layernorm": false, | |
| "resid_pdrop": 0.2, | |
| "rope_scaling": { | |
| "factor": 2.0, | |
| "rope_type": "linear", | |
| "type": "linear" | |
| }, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.1", | |
| "use_cache": true, | |
| "vocab_size": 128 | |
| } | |