| { |
| "_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": "13", |
| "6": "14", |
| "7": "15", |
| "8": "16", |
| "9": "17", |
| "10": "18", |
| "11": "19", |
| "12": "2", |
| "13": "20", |
| "14": "21", |
| "15": "22", |
| "16": "3", |
| "17": "4", |
| "18": "5", |
| "19": "6", |
| "20": "7", |
| "21": "8", |
| "22": "9" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 10240, |
| "label2id": { |
| "0": 0, |
| "1": 1, |
| "10": 2, |
| "11": 3, |
| "12": 4, |
| "13": 5, |
| "14": 6, |
| "15": 7, |
| "16": 8, |
| "17": 9, |
| "18": 10, |
| "19": 11, |
| "2": 12, |
| "20": 13, |
| "21": 14, |
| "22": 15, |
| "3": 16, |
| "4": 17, |
| "5": 18, |
| "6": 19, |
| "7": 20, |
| "8": 21, |
| "9": 22 |
| }, |
| "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 |
| } |
|
|
