bradmin/rm_trl
07
1{2 "_name_or_path": "klue/roberta-base",3 "architectures": [4 "RobertaForSequenceClassification"5 ],6 "attention_probs_dropout_prob": 0.1,7 "bos_token_id": 0,8 "classifier_dropout": null,9 "eos_token_id": 2,10 "gradient_checkpointing": false,11 "hidden_act": "gelu",12 "hidden_dropout_prob": 0.1,13 "hidden_size": 768,14 "id2label": {15 "0": "LABEL_0"16 },17 "initializer_range": 0.02,18 "intermediate_size": 3072,19 "label2id": {20 "LABEL_0": 021 },22 "layer_norm_eps": 1e-05,23 "max_position_embeddings": 514,24 "model_type": "roberta",25 "num_attention_heads": 12,26 "num_hidden_layers": 12,27 "pad_token_id": 1,28 "position_embedding_type": "absolute",29 "tokenizer_class": "BertTokenizer",30 "torch_dtype": "bfloat16",31 "transformers_version": "4.31.0",32 "type_vocab_size": 1,33 "use_cache": true,34 "vocab_size": 3200035}36 