Commit 
							
							·
						
						35c2c6f
	
1
								Parent(s):
							
							68600c6
								
add model
Browse files- config.json +48 -0
 - pytorch_model.bin +3 -0
 
    	
        config.json
    ADDED
    
    | 
         @@ -0,0 +1,48 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "_name_or_path": "few_shot_model_yahoo",
         
     | 
| 3 | 
         
            +
              "_num_labels": 3,
         
     | 
| 4 | 
         
            +
              "activation_dropout": 0.0,
         
     | 
| 5 | 
         
            +
              "activation_function": "gelu",
         
     | 
| 6 | 
         
            +
              "architectures": [
         
     | 
| 7 | 
         
            +
                "BartForSequenceClassification"
         
     | 
| 8 | 
         
            +
              ],
         
     | 
| 9 | 
         
            +
              "attention_dropout": 0.0,
         
     | 
| 10 | 
         
            +
              "bos_token_id": 0,
         
     | 
| 11 | 
         
            +
              "classif_dropout": 0.0,
         
     | 
| 12 | 
         
            +
              "classifier_dropout": 0.0,
         
     | 
| 13 | 
         
            +
              "d_model": 1024,
         
     | 
| 14 | 
         
            +
              "decoder_attention_heads": 16,
         
     | 
| 15 | 
         
            +
              "decoder_ffn_dim": 4096,
         
     | 
| 16 | 
         
            +
              "decoder_layerdrop": 0.0,
         
     | 
| 17 | 
         
            +
              "decoder_layers": 12,
         
     | 
| 18 | 
         
            +
              "decoder_start_token_id": 2,
         
     | 
| 19 | 
         
            +
              "dropout": 0.1,
         
     | 
| 20 | 
         
            +
              "encoder_attention_heads": 16,
         
     | 
| 21 | 
         
            +
              "encoder_ffn_dim": 4096,
         
     | 
| 22 | 
         
            +
              "encoder_layerdrop": 0.0,
         
     | 
| 23 | 
         
            +
              "encoder_layers": 12,
         
     | 
| 24 | 
         
            +
              "eos_token_id": 2,
         
     | 
| 25 | 
         
            +
              "forced_eos_token_id": 2,
         
     | 
| 26 | 
         
            +
              "gradient_checkpointing": false,
         
     | 
| 27 | 
         
            +
              "id2label": {
         
     | 
| 28 | 
         
            +
                "0": "contradiction",
         
     | 
| 29 | 
         
            +
                "1": "neutral",
         
     | 
| 30 | 
         
            +
                "2": "entailment"
         
     | 
| 31 | 
         
            +
              },
         
     | 
| 32 | 
         
            +
              "init_std": 0.02,
         
     | 
| 33 | 
         
            +
              "is_encoder_decoder": true,
         
     | 
| 34 | 
         
            +
              "label2id": {
         
     | 
| 35 | 
         
            +
                "contradiction": 0,
         
     | 
| 36 | 
         
            +
                "entailment": 2,
         
     | 
| 37 | 
         
            +
                "neutral": 1
         
     | 
| 38 | 
         
            +
              },
         
     | 
| 39 | 
         
            +
              "max_position_embeddings": 1024,
         
     | 
| 40 | 
         
            +
              "model_type": "bart",
         
     | 
| 41 | 
         
            +
              "num_hidden_layers": 12,
         
     | 
| 42 | 
         
            +
              "output_past": false,
         
     | 
| 43 | 
         
            +
              "pad_token_id": 1,
         
     | 
| 44 | 
         
            +
              "scale_embedding": false,
         
     | 
| 45 | 
         
            +
              "transformers_version": "4.8.2",
         
     | 
| 46 | 
         
            +
              "use_cache": true,
         
     | 
| 47 | 
         
            +
              "vocab_size": 50265
         
     | 
| 48 | 
         
            +
            }
         
     | 
    	
        pytorch_model.bin
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:14ec8fd9dae3e0716d992396dded29bc1cb9149e51d2d8e4c2825ab4e7089e68
         
     | 
| 3 | 
         
            +
            size 1629572938
         
     |