Upload 6 files

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "monologg/kobigbird-bert-base",
+  "architectures": [
+    "BigBirdForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "rescale_embeddings": false,
+  "sep_token_id": 3,
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 32500
+}

finetune_config.json

@@ -0,0 +1,35 @@
+{
+    "adam_epsilon": 1e-08,
+    "all_korquad_2_sample": false,
+    "cache_dir": "cache",
+    "data_dir": "cache/korquad_2",
+    "dataset": "korquad_2",
+    "do_eval": true,
+    "do_eval_during_train": true,
+    "do_lower_case": false,
+    "do_train": true,
+    "doc_stride": 3072,
+    "eval_batch_size": 1,
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 3e-05,
+    "max_answer_length": 4096,
+    "max_grad_norm": 1.0,
+    "max_query_length": 64,
+    "max_seq_length": 4096,
+    "model_name_or_path": "monologg/kobigbird-bert-base",
+    "n_best_size": 20,
+    "null_score_diff_threshold": 0.0,
+    "num_train_epochs": 5,
+    "output_dir": "output",
+    "predict_file": "dev",
+    "seed": 42,
+    "task": "qa",
+    "threads": 4,
+    "train_batch_size": 2,
+    "train_file": "train",
+    "use_tpu": true,
+    "version_2_with_negative": false,
+    "warmup_proportion": 0.0,
+    "weight_decay": 0.0,
+    "world_size": 8
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c06c8b4d3f5ede061c9d5c28a485ac31ea9b87f0e706cdc9de61e0cdf8ef148
+size 471671149

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 4096, "name_or_path": "monologg/kobigbird-bert-base", "tokenizer_class": "BertTokenizer"}