MyCustomReader

language_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2097bbdd356517624f043f6577b5afe26a35968e763dd3296d5f03256864c77
+size 265489795

language_model_config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased-distilled-squad",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "language": "english",
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "name": "DistilBert",
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.29.1",
+  "vocab_size": 30522
+}

prediction_head_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81c882a86ef9cc069b0d6a077161af56c224c0ac548a30a9b2b50dc99508e90
+size 7701

prediction_head_0_config.json

@@ -0,0 +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

@@ -0,0 +1 @@
+{"data_dir": "data", "dev_filename": "dev-v2.0.json", "dev_split": 0, "doc_stride": 128, "max_answers": null, "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

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}