| { | |
| "_name_or_path": "models/final/models_singleclass_google_mt5-base_class_weights=False_labels=hf_languages=combination_train.csv_bs=16_lr=5e-05_epoch=3_checkpoint-2250__class_weights=False_labels=Sub1_Toxic_languages=train.train.normalized.oversampling.csv_bs=16_lr=5e-05_epo", | |
| "architectures": [ | |
| "MT5ForConditionalGeneration" | |
| ], | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "mt5", | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "transformers_version": "4.6.0", | |
| "use_cache": true, | |
| "vocab_size": 250112 | |
| } | |