| { |
| "_name_or_path": "bert-base-multilingual-cased", |
| "architectures": [ |
| "BertForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "directionality": "bidi", |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "too-strict\n", |
| "1": "ok\n", |
| "2": "too-loose\n", |
| "3": "not-applicable\n" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "not-applicable\n": 3, |
| "ok\n": 1, |
| "too-loose\n": 2, |
| "too-strict\n": 0 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 0, |
| "pooler_fc_size": 768, |
| "pooler_num_attention_heads": 12, |
| "pooler_num_fc_layers": 3, |
| "pooler_size_per_head": 128, |
| "pooler_type": "first_token_transform", |
| "type_vocab_size": 2, |
| "vocab_size": 119547 |
| } |
|
|
