| { | |
| "_name_or_path": "megatron-bert-large-swedish-cased-165k.QM", | |
| "architectures": [ | |
| "MegatronBertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "finetuning_task": "mnli", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "entailment", | |
| "1": "neutral", | |
| "2": "contradiction" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "label2id": { | |
| "contradiction": 2, | |
| "entailment": 0, | |
| "neutral": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "megatron-bert", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "problem_type": "single_label_classification", | |
| "tokenizer_type": "BertWordPieceCase", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.24.0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 64128 | |
| } | |