support FEATS

README.md

@@ -16,7 +16,7 @@ pipeline_tag: "token-classification"
 
 ## Model Description
 
-This is a RoBERTa model pre-trained with [UD_Belarusian](https://universaldependencies.org/be/) for POS-tagging and dependency-parsing, derived from [roberta-small-belarusian](https://huggingface.co/KoichiYasuoka/roberta-small-belarusian). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
+This is a RoBERTa model pre-trained with [UD_Belarusian](https://universaldependencies.org/be/) for POS-tagging and dependency-parsing, derived from [roberta-small-belarusian](https://huggingface.co/KoichiYasuoka/roberta-small-belarusian). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
 
 ## How to Use
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34bc0dc5b64ff4fda738470268c2dc17f9267a6b58e14d260abcf8d68ef914dc
-size 62598033
+oid sha256:e88de02a3f91872ee09e6f549bdc82c3628324292753c7d993d87157c3dc2ec2
+size 64936550

special_tokens_map.json

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

supar.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70647136e8bce1ad7f73a3a1624f1046a1834a6a85bbef5c464e73eb1337f56
-size 117684157
+oid sha256:f76dfefac807718021e6d27c94af65ea44e2b0ffc28007adb8bb50ad6309ab7a
+size 117746294

tokenizer_config.json

@@ -1 +1,64 @@
-{"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": false, "do_lowercase": false, "never_split": ["[CLS]", "[PAD]", "[SEP]", "[UNK]", "[MASK]"], "do_basic_tokenize": true, "model_max_length": 128, "tokenizer_class": "BertTokenizerFast"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "do_lowercase": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "never_split": [
+    "[CLS]",
+    "[PAD]",
+    "[SEP]",
+    "[UNK]",
+    "[MASK]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}