| { |
| "architectures": [ |
| "T5ForSequenceClassification" |
| ], |
| "classifier_dropout": 0.0, |
| "d_ff": 2048, |
| "d_kv": 64, |
| "d_model": 512, |
| "decoder_start_token_id": 0, |
| "dense_act_fn": "relu", |
| "dropout_rate": 0.1, |
| "dtype": "float32", |
| "eos_token_id": 1, |
| "feed_forward_proj": "relu", |
| "id2label": { |
| "0": "ach", |
| "1": "adh", |
| "2": "bfa", |
| "3": "cgg", |
| "4": "eng", |
| "5": "gwr", |
| "6": "kdi", |
| "7": "kdj", |
| "8": "keo", |
| "9": "kin", |
| "10": "kpz", |
| "11": "laj", |
| "12": "lgg", |
| "13": "lsm", |
| "14": "luc", |
| "15": "lug", |
| "16": "mhi", |
| "17": "myx", |
| "18": "ndp", |
| "19": "nuj", |
| "20": "nyn", |
| "21": "nyo", |
| "22": "rub", |
| "23": "swa", |
| "24": "teo", |
| "25": "tlj", |
| "26": "ttj", |
| "27": "xog" |
| }, |
| "initializer_factor": 1.0, |
| "is_encoder_decoder": true, |
| "is_gated_act": false, |
| "label2id": { |
| "ach": 0, |
| "adh": 1, |
| "bfa": 2, |
| "cgg": 3, |
| "eng": 4, |
| "gwr": 5, |
| "kdi": 6, |
| "kdj": 7, |
| "keo": 8, |
| "kin": 9, |
| "kpz": 10, |
| "laj": 11, |
| "lgg": 12, |
| "lsm": 13, |
| "luc": 14, |
| "lug": 15, |
| "mhi": 16, |
| "myx": 17, |
| "ndp": 18, |
| "nuj": 19, |
| "nyn": 20, |
| "nyo": 21, |
| "rub": 22, |
| "swa": 23, |
| "teo": 24, |
| "tlj": 25, |
| "ttj": 26, |
| "xog": 27 |
| }, |
| "layer_norm_epsilon": 1e-06, |
| "model_type": "t5", |
| "n_positions": 512, |
| "num_decoder_layers": 6, |
| "num_heads": 8, |
| "num_layers": 6, |
| "pad_token_id": 0, |
| "problem_type": "single_label_classification", |
| "relative_attention_max_distance": 128, |
| "relative_attention_num_buckets": 32, |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "vocab_size": 32128 |
| } |
|
|
