Upload 9 files
Browse files- language_model.bin +3 -0
- language_model_config.json +25 -0
- prediction_head_0.bin +3 -0
- prediction_head_0_config.json +1 -0
- processor_config.json +1 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
    	
        language_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:875122b6c11f66bcfde6540dd7aab391032ecc2b4cec7b54f494765f8af16758
         | 
| 3 | 
            +
            size 265489795
         | 
    	
        language_model_config.json
    ADDED
    
    | @@ -0,0 +1,25 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "distilbert-base-uncased-distilled-squad",
         | 
| 3 | 
            +
              "activation": "gelu",
         | 
| 4 | 
            +
              "architectures": [
         | 
| 5 | 
            +
                "DistilBertForQuestionAnswering"
         | 
| 6 | 
            +
              ],
         | 
| 7 | 
            +
              "attention_dropout": 0.1,
         | 
| 8 | 
            +
              "dim": 768,
         | 
| 9 | 
            +
              "dropout": 0.1,
         | 
| 10 | 
            +
              "hidden_dim": 3072,
         | 
| 11 | 
            +
              "initializer_range": 0.02,
         | 
| 12 | 
            +
              "language": "english",
         | 
| 13 | 
            +
              "max_position_embeddings": 512,
         | 
| 14 | 
            +
              "model_type": "distilbert",
         | 
| 15 | 
            +
              "n_heads": 12,
         | 
| 16 | 
            +
              "n_layers": 6,
         | 
| 17 | 
            +
              "name": "DistilBert",
         | 
| 18 | 
            +
              "pad_token_id": 0,
         | 
| 19 | 
            +
              "qa_dropout": 0.1,
         | 
| 20 | 
            +
              "seq_classif_dropout": 0.2,
         | 
| 21 | 
            +
              "sinusoidal_pos_embds": false,
         | 
| 22 | 
            +
              "tie_weights_": true,
         | 
| 23 | 
            +
              "transformers_version": "4.25.1",
         | 
| 24 | 
            +
              "vocab_size": 30522
         | 
| 25 | 
            +
            }
         | 
    	
        prediction_head_0.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:f38adf2c7fbf38a6075f5ea4a3733b75bc5b485fe563da81e85244cc98bedca2
         | 
| 3 | 
            +
            size 7701
         | 
    	
        prediction_head_0_config.json
    ADDED
    
    | @@ -0,0 +1 @@ | |
|  | 
|  | |
| 1 | 
            +
            {"training": true, "layer_dims": [768, 2], "num_labels": 2, "ph_output_type": "per_token_squad", "model_type": "span_classification", "task_name": "question_answering", "no_ans_boost": 0.0, "context_window_size": 150, "n_best": 4, "n_best_per_sample": 1, "duplicate_filtering": 0, "use_confidence_scores_for_ranking": true, "use_no_answer_legacy_confidence": false, "label_tensor_name": "question_answering_label_ids", "label_list": ["start_token", "end_token"], "metric": "squad", "name": "QuestionAnsweringHead"}
         | 
    	
        processor_config.json
    ADDED
    
    | @@ -0,0 +1 @@ | |
|  | 
|  | |
| 1 | 
            +
            {"data_dir": "data", "dev_filename": "dev-v2.0.json", "dev_split": 0, "doc_stride": 128, "max_answers": 6, "max_query_length": 64, "max_seq_len": 256, "multithreading_rust": true, "ph_output_type": "per_token_squad", "proxies": null, "sp_toks_end": 1, "sp_toks_mid": 1, "sp_toks_start": 1, "tasks": {"question_answering": {"label_list": ["start_token", "end_token"], "metric": "squad", "label_tensor_name": "question_answering_label_ids", "label_name": "question_answering_label", "label_column_name": null, "text_column_name": null, "task_type": null}}, "test_filename": null, "train_filename": "train-v2.0.json", "tokenizer": "DistilBertTokenizerFast", "processor": "SquadProcessor"}
         | 
    	
        special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,7 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "cls_token": "[CLS]",
         | 
| 3 | 
            +
              "mask_token": "[MASK]",
         | 
| 4 | 
            +
              "pad_token": "[PAD]",
         | 
| 5 | 
            +
              "sep_token": "[SEP]",
         | 
| 6 | 
            +
              "unk_token": "[UNK]"
         | 
| 7 | 
            +
            }
         | 
    	
        tokenizer.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1,14 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "cls_token": "[CLS]",
         | 
| 3 | 
            +
              "do_lower_case": true,
         | 
| 4 | 
            +
              "mask_token": "[MASK]",
         | 
| 5 | 
            +
              "model_max_length": 512,
         | 
| 6 | 
            +
              "name_or_path": "distilbert-base-uncased-distilled-squad",
         | 
| 7 | 
            +
              "pad_token": "[PAD]",
         | 
| 8 | 
            +
              "sep_token": "[SEP]",
         | 
| 9 | 
            +
              "special_tokens_map_file": null,
         | 
| 10 | 
            +
              "strip_accents": null,
         | 
| 11 | 
            +
              "tokenize_chinese_chars": true,
         | 
| 12 | 
            +
              "tokenizer_class": "DistilBertTokenizer",
         | 
| 13 | 
            +
              "unk_token": "[UNK]"
         | 
| 14 | 
            +
            }
         | 
    	
        vocab.txt
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  |