Model save

.gitattributes

@@ -31,3 +31,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,11 +1,12 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "BertForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -45,16 +46,17 @@
     "I-TaskName": 12,
     "O": 0
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.23.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0edc3c3a5f089e054b40e039cf6777e4f97080b41ccc77fb9b05402625cdf9d
-size 431000439
+oid sha256:7c5e1ca19ced20fb6cf0e8849a433d4988e5fa08139a0af2ab5bf2a7b9534891
+size 1109934583

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,14 +1,20 @@
 {
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "model_max_length": 512,
-  "name_or_path": "bert-base-cased",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "name_or_path": "xlm-roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
   "special_tokens_map_file": null,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea1cc0a976aed4f67e50ba59271be4f1fe620e0ff8eda9551febb5d0dbdca6c
+oid sha256:5d63069587d2113dd2203daa51da99771b0e67b36e11e5482331f27e9ca6cae0
 size 3375