janpase97/codeformer-pretrained
370
1{2 "activation_dropout": 0.0,3 "activation_function": "gelu",4 "architectures": [5 "BartForConditionalGeneration"6 ],7 "attention_dropout": 0.0,8 "bos_token_id": 3,9 "classifier_dropout": 0.0,10 "d_model": 1024,11 "decoder_attention_heads": 16,12 "decoder_ffn_dim": 4096,13 "decoder_layerdrop": 0.0,14 "decoder_layers": 12,15 "decoder_start_token_id": 3,16 "dropout": 0.1,17 "encoder_attention_heads": 16,18 "encoder_ffn_dim": 4096,19 "encoder_layerdrop": 0.0,20 "encoder_layers": 12,21 "eos_token_id": 4,22 "force_bos_token_to_be_generated": true,23 "forced_bos_token_id": 3,24 "forced_eos_token_id": 4,25 "gradient_checkpointing": false,26 "id2label": {27 "0": "LABEL_0",28 "1": "LABEL_1",29 "2": "LABEL_2"30 },31 "init_std": 0.02,32 "is_encoder_decoder": true,33 "label2id": {34 "LABEL_0": 0,35 "LABEL_1": 1,36 "LABEL_2": 237 },38 "max_position_embeddings": 1024,39 "model_type": "bart",40 "num_hidden_layers": 12,41 "pad_token_id": 1,42 "scale_embedding": false,43 "sep_token_id": 5,44 "transformers_version": "4.6.1",45 "use_cache": true,46 "vocab_size": 2500047}48 