model improved

README.md

@@ -16,7 +16,7 @@ pipeline_tag: "token-classification"
 
 ## Model Description
 
-This is a RoBERTa model pre-trained on Chinese texts (both simplified and traditional) for POS-tagging and dependency-parsing (using `goeswith` for subwords), derived from [roberta-base-chinese-upos](https://huggingface.co/KoichiYasuoka/roberta-base-chinese-upos).
+This is a RoBERTa model pre-trained on Chinese Wikipedia texts (both simplified and traditional) for POS-tagging and dependency-parsing (using `goeswith` for subwords), derived from [roberta-base-chinese-upos](https://huggingface.co/KoichiYasuoka/roberta-base-chinese-upos).
 
 ## How to Use
 

config.json

@@ -10,7 +10,6 @@
       "impl": "ud.UniversalDependenciesPipeline"
     }
   },
-  "directionality": "bidi",
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -633,16 +632,11 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "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",
   "tokenizer_class": "BertTokenizerFast",
   "torch_dtype": "float32",
   "transformers_version": "4.22.1",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 21597
+  "vocab_size": 26582
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d46ab28f34d65e8cd28c870bc9ca6e8d10d012e9a900df272620a292b67f5825
-size 409151985
+oid sha256:3b4195111b8295c7cfa9abd1def9e84fef30abb99a4e61d33285b8642ee3bd1f
+size 424465905

tokenizer_config.json

@@ -1,13 +1,19 @@
 {
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "never_split": null,
+  "never_split": [
+    "[CLS]",
+    "[PAD]",
+    "[SEP]",
+    "[UNK]",
+    "[MASK]"
+  ],
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
+  "strip_accents": false,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizerFast",
   "unk_token": "[UNK]"