{ "_name_or_path": "versae/gzip-bert", "architectures": [ "RoFormerForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "embedding_size": 768, "hidden_act": "relu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "NEGATIVE", "1": "POSITIVE" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "NEGATIVE": 0, "POSITIVE": 1 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "roformer", "norm_type": "rms_norm", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "problem_type": "single_label_classification", "rotary_value": false, "torch_dtype": "float32", "transformers_version": "4.31.0", "type_vocab_size": 2, "use_bias": false, "use_cache": true, "vocab_size": 12000 }