Upload 10 files

language_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad57bab6dbdfeb1cd3848ad84cc585eab14f2d71a36d69c2226f8a2737380fd3
+size 439792945

language_model_config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "IVN-RIN/bioBIT",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "name": "Bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

prediction_head_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17af7496c3dd2eb092914c20d385e65a1da90443e222506d4830664f528c344f
+size 7587

prediction_head_0_config.json

@@ -0,0 +1 @@
+{"training": false, "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": 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": "BertTokenizerFast", "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]"
+}

test_performance.json

@@ -0,0 +1,16 @@
+{
+    "EM": 78.12244897959184,
+    "f1": 84.74487389969126,
+    "top_n_accuracy": 97.83673469387755,
+    "top_n": 4,
+    "EM_text_answer": 66.49316851008457,
+    "f1_text_answer": 77.0494086234506,
+    "top_n_accuracy_text_answer": 96.55172413793103,
+    "top_n_EM_text_answer": 71.17761873780091,
+    "top_n_f1_text_answer": 88.40625292515978,
+    "Total_text_answer": 1537,
+    "EM_no_answer": 97.69989047097481,
+    "f1_no_answer": 97.69989047097481,
+    "top_n_accuracy_no_answer": 100.0,
+    "Total_no_answer": 913
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "name_or_path": "IVN-RIN/bioBIT",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation": true,
+  "unk_token": "[UNK]"
+}