| { | |
| "_name_or_path": "/rscratch/nehrdich/ByT5-Sanskrit/results/TranslationChineseWMT21Experiment/checkpoint-synthetic/", | |
| "activation_dropout": 0.0, | |
| "activation_function": "relu", | |
| "architectures": [ | |
| "M2M100ForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 0, | |
| "d_model": 2048, | |
| "decoder_attention_heads": 32, | |
| "decoder_ffn_dim": 16384, | |
| "decoder_layerdrop": 0, | |
| "decoder_layers": 24, | |
| "decoder_start_token_id": 2, | |
| "dropout": 0.1, | |
| "early_stopping": true, | |
| "encoder_attention_heads": 32, | |
| "encoder_ffn_dim": 16384, | |
| "encoder_layerdrop": 0, | |
| "encoder_layers": 24, | |
| "eos_token_id": 2, | |
| "forced_bos_token_id": 128001, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "max_length": 256, | |
| "max_position_embeddings": 1024, | |
| "model_type": "m2m_100", | |
| "num_beams": 5, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": 1, | |
| "scale_embedding": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.1", | |
| "use_cache": true, | |
| "vocab_size": 128009 | |
| } | |