| { | |
| "_name_or_path": "/data/scratch/svanhvit/byt5/byt5-base-finetuned-35M-is_err-to-is_corr-max-len-512-bz-8/checkpoint-510000", | |
| "architectures": [ | |
| "T5ForConditionalGeneration" | |
| ], | |
| "d_ff": 3968, | |
| "d_kv": 64, | |
| "d_model": 1536, | |
| "decoder_start_token_id": 0, | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "gradient_checkpointing": false, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "num_decoder_layers": 6, | |
| "num_heads": 12, | |
| "num_layers": 18, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "ByT5Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.19.2", | |
| "use_cache": true, | |
| "vocab_size": 384, | |
| "max_length": 512, | |
| "task_specific_params": { | |
| "text2text-generation": { | |
| "max_length": 512 | |
| } | |
| }, | |
| } | |