| { | |
| "architectures": [ | |
| "FSMTForConditionalGeneration" | |
| ], | |
| "model_type": "fsmt", | |
| "activation_dropout": 0.0, | |
| "activation_function": "relu", | |
| "attention_dropout": 0.1, | |
| "d_model": 1024, | |
| "dropout": 0.2, | |
| "init_std": 0.02, | |
| "max_position_embeddings": 1024, | |
| "num_hidden_layers": 6, | |
| "src_vocab_size": 31640, | |
| "tgt_vocab_size": 31232, | |
| "langs": [ | |
| "en", | |
| "ru" | |
| ], | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 8192, | |
| "encoder_layerdrop": 0, | |
| "encoder_layers": 6, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0, | |
| "decoder_layers": 6, | |
| "bos_token_id": 0, | |
| "pad_token_id": 1, | |
| "eos_token_id": 2, | |
| "is_encoder_decoder": true, | |
| "scale_embedding": true, | |
| "tie_word_embeddings": false, | |
| "num_beams": 5, | |
| "early_stopping": false, | |
| "length_penalty": 1.15 | |
| } |