Update config.json
Browse files- config.json +37 -0
 
    	
        config.json
    ADDED
    
    | 
         @@ -0,0 +1,37 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "architectures": [
         
     | 
| 3 | 
         
            +
                "FSMTForConditionalGeneration"
         
     | 
| 4 | 
         
            +
              ],
         
     | 
| 5 | 
         
            +
              "model_type": "fsmt",
         
     | 
| 6 | 
         
            +
              "activation_dropout": 0.0,
         
     | 
| 7 | 
         
            +
              "activation_function": "relu",
         
     | 
| 8 | 
         
            +
              "attention_dropout": 0.1,
         
     | 
| 9 | 
         
            +
              "d_model": 1024,
         
     | 
| 10 | 
         
            +
              "dropout": 0.2,
         
     | 
| 11 | 
         
            +
              "init_std": 0.02,
         
     | 
| 12 | 
         
            +
              "max_position_embeddings": 1024,
         
     | 
| 13 | 
         
            +
              "num_hidden_layers": 6,
         
     | 
| 14 | 
         
            +
              "src_vocab_size": 31232,
         
     | 
| 15 | 
         
            +
              "tgt_vocab_size": 31640,
         
     | 
| 16 | 
         
            +
              "langs": [
         
     | 
| 17 | 
         
            +
                "ru",
         
     | 
| 18 | 
         
            +
                "en"
         
     | 
| 19 | 
         
            +
              ],
         
     | 
| 20 | 
         
            +
              "encoder_attention_heads": 16,
         
     | 
| 21 | 
         
            +
              "encoder_ffn_dim": 8192,
         
     | 
| 22 | 
         
            +
              "encoder_layerdrop": 0,
         
     | 
| 23 | 
         
            +
              "encoder_layers": 6,
         
     | 
| 24 | 
         
            +
              "decoder_attention_heads": 16,
         
     | 
| 25 | 
         
            +
              "decoder_ffn_dim": 4096,
         
     | 
| 26 | 
         
            +
              "decoder_layerdrop": 0,
         
     | 
| 27 | 
         
            +
              "decoder_layers": 6,
         
     | 
| 28 | 
         
            +
              "bos_token_id": 0,
         
     | 
| 29 | 
         
            +
              "pad_token_id": 1,
         
     | 
| 30 | 
         
            +
              "eos_token_id": 2,
         
     | 
| 31 | 
         
            +
              "is_encoder_decoder": true,
         
     | 
| 32 | 
         
            +
              "scale_embedding": true,
         
     | 
| 33 | 
         
            +
              "tie_word_embeddings": false,
         
     | 
| 34 | 
         
            +
              "num_beams": 5,
         
     | 
| 35 | 
         
            +
              "early_stopping": false,
         
     | 
| 36 | 
         
            +
              "length_penalty": 1.1
         
     | 
| 37 | 
         
            +
            }
         
     |