init

README.md

@@ -0,0 +1,33 @@
+---
+language: 
+- "zh"
+thumbnail: "https://user-images.githubusercontent.com/9592150/97142000-cad08e00-179a-11eb-88df-aff9221482d8.png"
+tags:
+- "chinese"
+- "classical chinese"
+- "literary chinese"
+- "ancient chinese"
+- "bert"
+- "pytorch"
+- "sentence segmentation"
+license: "apache-2.0"
+pipeline_tag: "token-classification"
+widget:
+- text: "及秦始皇灭先代典籍焚书坑儒天下学士逃难解散我先人用藏其家书于屋壁汉室龙兴开设学校旁求儒雅以阐大猷济南伏生年过九十失其本经口以传授裁二十馀篇以其上古之书谓之尚书百篇之义世莫得闻"
+---
+
+# Guwen Seg
+
+A Classical Chinese Sentence Segmenter.
+
+See also: 
+
+<a href="https://github.com/ethan-yt/guwen-models">
+  <img align="center" width="400" src="https://github-readme-stats.vercel.app/api/pin/?username=ethan-yt&repo=guwen-models&bg_color=30,e96443,904e95&title_color=fff&text_color=fff&icon_color=fff&show_owner=true" />
+</a>
+<a href="https://github.com/ethan-yt/cclue/">
+  <img align="center" width="400" src="https://github-readme-stats.vercel.app/api/pin/?username=ethan-yt&repo=cclue&bg_color=30,e96443,904e95&title_color=fff&text_color=fff&icon_color=fff&show_owner=true" />
+</a>
+<a href="https://github.com/ethan-yt/guwenbert/">
+  <img align="center" width="400" src="https://github-readme-stats.vercel.app/api/pin/?username=ethan-yt&repo=guwenbert&bg_color=30,e96443,904e95&title_color=fff&text_color=fff&icon_color=fff&show_owner=true" />
+</a>

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "output/guwenbert-fs/seg/checkpoint-1700",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "seg",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "B": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "transformers_version": "4.5.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 23292
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec6318c6f5c4606be3eaa4e2b47d52e52a8528a4f5457d20e4a8fea059dff47
+size 413455031

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "use_fast": true, "special_tokens_map_file": "models/guwenbert-base-fs/special_tokens_map.json", "name_or_path": "models/guwenbert-base-fs", "do_basic_tokenize": true, "never_split": null}