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"
+- "text classificatio"
+license: "apache-2.0"
+pipeline_tag: "text-classification"
+widget:
+- text: "子曰：“弟子入则孝，出则悌，谨而信，泛爱众，而亲仁。行有馀力，则以学文。”"
+---
+
+# Guwen CLS
+
+A Classical Chinese Text Classifier.
+
+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 +1,52 @@
+{
+  "_name_or_path": "output/guwenbert-fs/text_classification/checkpoint-12000",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "text_classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "易藏",
+    "1": "医藏",
+    "2": "艺藏",
+    "3": "史藏",
+    "4": "佛藏",
+    "5": "集藏",
+    "6": "诗藏",
+    "7": "子藏",
+    "8": "儒藏",
+    "9": "道藏"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "易藏": 0,
+    "医藏": 1,
+    "艺藏": 2,
+    "史藏": 3,
+    "佛藏": 4,
+    "集藏": 5,
+    "诗藏": 6,
+    "子藏": 7,
+    "儒藏": 8,
+    "道藏": 9
+  },
+  "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 sha256:69704266ee4da58564c6125f4d5fad736f581a167aa83dad839d07fb1cc7ac6a
+size 415842761

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}