model improved

maker.py

@@ -0,0 +1,9 @@
+#! /usr/bin/python3
+src="KoichiYasuoka/roberta-base-ukrainian"
+tgt="KoichiYasuoka/roberta-base-ukrainian-upos"
+import os,sys
+os.system("test -d UD_Ukrainian-IU || git clone --depth=1 https://github.com/UniversalDependencies/UD_Ukrainian-IU")
+os.system("test -d UD_Ukrainian-ParlaMint || git clone --depth=1 https://github.com/UniversalDependencies/UD_Ukrainian-ParlaMint")
+os.system("for F in train dev test ; do cat UD_Ukrainian-*/*-$F.conllu > $F.conllu ; done ; cat *.conllu > train.upos")
+os.system(f"{sys.executable} -m esupar.train {src} {tgt} -16 /tmp train.upos")
+os.system(f"{sys.executable} -m esupar.train {tgt} {tgt} 16 /// train.conllu dev.conllu test.conllu")

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59124a679ed7e8a21c1af7e5492523d31f566c8266291d6b681970dd85193f05
-size 434378481
+oid sha256:4674870b5d778e8f42d84a31fc87f0b3e4e5bef406725a41b34ae55b1b62a0a6
+size 444976166

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 sha256:743f9e0b64332261598f5989a76afcbab67e5569c4286496f8f775fed2a6a14f
-size 594683109
+oid sha256:6af43c53e31b499c51d195c4402ae03b8b3554167f967e438debb94b15bbd4c7
+size 489051894

tokenizer_config.json

@@ -1 +1,65 @@
-{"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, "lowercase": false, "never_split": ["[CLS]", "[PAD]", "[SEP]", "[UNK]", "[MASK]"], "do_basic_tokenize": true, "model_max_length": 512, "tokenizer_class": "BertTokenizerFast"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "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,
+  "extra_special_tokens": {},
+  "lowercase": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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]"
+}