Commit 
							
							·
						
						bdd2b34
	
1
								Parent(s):
							
							7262c4f
								
Uploaded model and weights
Browse files- config.json +73 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,73 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "facebook/bart-base",
         | 
| 3 | 
            +
              "activation_dropout": 0.1,
         | 
| 4 | 
            +
              "activation_function": "gelu",
         | 
| 5 | 
            +
              "add_bias_logits": false,
         | 
| 6 | 
            +
              "add_final_layer_norm": false,
         | 
| 7 | 
            +
              "architectures": [
         | 
| 8 | 
            +
                "BartForConditionalGeneration"
         | 
| 9 | 
            +
              ],
         | 
| 10 | 
            +
              "attention_dropout": 0.1,
         | 
| 11 | 
            +
              "bos_token_id": 0,
         | 
| 12 | 
            +
              "classif_dropout": 0.1,
         | 
| 13 | 
            +
              "classifier_dropout": 0.0,
         | 
| 14 | 
            +
              "d_model": 768,
         | 
| 15 | 
            +
              "decoder_attention_heads": 12,
         | 
| 16 | 
            +
              "decoder_ffn_dim": 3072,
         | 
| 17 | 
            +
              "decoder_layerdrop": 0.0,
         | 
| 18 | 
            +
              "decoder_layers": 6,
         | 
| 19 | 
            +
              "decoder_start_token_id": 2,
         | 
| 20 | 
            +
              "dropout": 0.1,
         | 
| 21 | 
            +
              "early_stopping": true,
         | 
| 22 | 
            +
              "encoder_attention_heads": 12,
         | 
| 23 | 
            +
              "encoder_ffn_dim": 3072,
         | 
| 24 | 
            +
              "encoder_layerdrop": 0.0,
         | 
| 25 | 
            +
              "encoder_layers": 6,
         | 
| 26 | 
            +
              "eos_token_id": 2,
         | 
| 27 | 
            +
              "forced_eos_token_id": 2,
         | 
| 28 | 
            +
              "gradient_checkpointing": false,
         | 
| 29 | 
            +
              "id2label": {
         | 
| 30 | 
            +
                "0": "LABEL_0",
         | 
| 31 | 
            +
                "1": "LABEL_1",
         | 
| 32 | 
            +
                "2": "LABEL_2"
         | 
| 33 | 
            +
              },
         | 
| 34 | 
            +
              "init_std": 0.02,
         | 
| 35 | 
            +
              "is_encoder_decoder": true,
         | 
| 36 | 
            +
              "label2id": {
         | 
| 37 | 
            +
                "LABEL_0": 0,
         | 
| 38 | 
            +
                "LABEL_1": 1,
         | 
| 39 | 
            +
                "LABEL_2": 2
         | 
| 40 | 
            +
              },
         | 
| 41 | 
            +
              "max_position_embeddings": 1024,
         | 
| 42 | 
            +
              "model_type": "bart",
         | 
| 43 | 
            +
              "no_repeat_ngram_size": 3,
         | 
| 44 | 
            +
              "normalize_before": false,
         | 
| 45 | 
            +
              "normalize_embedding": true,
         | 
| 46 | 
            +
              "num_beams": 4,
         | 
| 47 | 
            +
              "num_hidden_layers": 6,
         | 
| 48 | 
            +
              "pad_token_id": 1,
         | 
| 49 | 
            +
              "scale_embedding": false,
         | 
| 50 | 
            +
              "task_specific_params": {
         | 
| 51 | 
            +
                "summarization": {
         | 
| 52 | 
            +
                  "length_penalty": 1.0,
         | 
| 53 | 
            +
                  "max_length": 128,
         | 
| 54 | 
            +
                  "min_length": 12,
         | 
| 55 | 
            +
                  "num_beams": 4
         | 
| 56 | 
            +
                },
         | 
| 57 | 
            +
                "summarization_cnn": {
         | 
| 58 | 
            +
                  "length_penalty": 2.0,
         | 
| 59 | 
            +
                  "max_length": 142,
         | 
| 60 | 
            +
                  "min_length": 56,
         | 
| 61 | 
            +
                  "num_beams": 4
         | 
| 62 | 
            +
                },
         | 
| 63 | 
            +
                "summarization_xsum": {
         | 
| 64 | 
            +
                  "length_penalty": 1.0,
         | 
| 65 | 
            +
                  "max_length": 62,
         | 
| 66 | 
            +
                  "min_length": 11,
         | 
| 67 | 
            +
                  "num_beams": 6
         | 
| 68 | 
            +
                }
         | 
| 69 | 
            +
              },
         | 
| 70 | 
            +
              "transformers_version": "4.8.2",
         | 
| 71 | 
            +
              "use_cache": true,
         | 
| 72 | 
            +
              "vocab_size": 50265
         | 
| 73 | 
            +
            }
         | 
    	
        merges.txt
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:644c24be674d54cd95f689ac80a8f9e87d428db5541c757d36bee4d4d90e39d6
         | 
| 3 | 
            +
            size 557979193
         | 
    	
        special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1 @@ | |
|  | 
|  | |
| 1 | 
            +
            {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
         | 
    	
        tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1 @@ | |
|  | 
|  | |
| 1 | 
            +
            {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
         | 
    	
        vocab.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
