Upload 8 files

outputs-macbert4csc_20240428


- ERNIE for Chinese Spelling Correction 繁體中文
- MacBertMaskedLM For Chinese Spelling Correction 繁體中文
- wikipedia-zh-20230720-filtered.json 繁體中文
- Automatic Corpus Generation-zh 繁體中文

- [那些自然語言處理 (Natural Language Processing, NLP) 踩的坑 -- 文本糾錯](https://blog.twman.org/2021/04/NLP.html#:~:text=%E4%BA%86%E9%BB%9E%E6%84%9F%E8%A6%BA%E3%80%82-,%E6%96%87%E6%9C%AC%E7%B3%BE%E9%8C%AF%E9%BB%98%E9%BB%98%E6%9B%B4%E6%96%B0,-%E5%BE%8C%E4%BE%86%E3%80%82%E3%80%82%E3%80%82%E7%96%AB%E6%83%85)

outputs-macbert4csc_20240428/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "hfl/chinese-macbert-base",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

outputs-macbert4csc_20240428/epoch=10-val_loss=0.01.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0804c10281bb861eed4b9bf42f12bc318a44ca249b54fa43e2299028cb4763e2
+size 1227782734

outputs-macbert4csc_20240428/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

outputs-macbert4csc_20240428/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b6b856ce2d32a3286f82e2fe0ecc6a4f326a4863bd291b12e707cb7d7a41c9
+size 409232246

outputs-macbert4csc_20240428/special_tokens_map.json

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

outputs-macbert4csc_20240428/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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}