| { | |
| "_name_or_path": "microsoft/phi-2", | |
| "architectures": [ | |
| "PhiForSequenceClassification" | |
| ], | |
| "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, | |
| "finetuning_task": "text-classification", | |
| "hidden_act": "gelu_new", | |
| "hidden_size": 2560, | |
| "id2label": { | |
| "0": "0", | |
| "1": "1", | |
| "2": "10", | |
| "3": "11", | |
| "4": "12", | |
| "5": "2", | |
| "6": "3", | |
| "7": "4", | |
| "8": "5", | |
| "9": "6", | |
| "10": "7", | |
| "11": "8", | |
| "12": "9" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "label2id": { | |
| "0": 0, | |
| "1": 1, | |
| "10": 2, | |
| "11": 3, | |
| "12": 4, | |
| "2": 5, | |
| "3": 6, | |
| "4": 7, | |
| "5": 8, | |
| "6": 9, | |
| "7": 10, | |
| "8": 11, | |
| "9": 12 | |
| }, | |
| "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, | |
| "pad_token_id": 50256, | |
| "partial_rotary_factor": 0.4, | |
| "problem_type": "single_label_classification", | |
| "qk_layernorm": false, | |
| "resid_pdrop": 0.1, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.39.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 50295 | |
| } | |