ernie -> xlm-robeta

.gitattributes

@@ -33,3 +33,4 @@ 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

@@ -1,10 +1,12 @@
 {
-  "_name_or_path": "nghuyong/ernie-3.0-base-zh",
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
   "architectures": [
-    "ErnieForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -47,18 +49,17 @@
     "\u95ee\u5019\u5bd2\u6684": 15
   },
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "ernie",
+  "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",
   "problem_type": "single_label_classification",
-  "task_type_vocab_size": 3,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "type_vocab_size": 4,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "use_task_id": true,
-  "vocab_size": 40000
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff1a06f045e680845302beaf4f40290c77b79dc88dec63e78904dce5e21199d
-size 471852384
+oid sha256:1d337bb927cffe618f01627666ac6609c7453a1f2cf2d0fb3f832f63885e0dfb
+size 1112248072

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[CLS]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[SEP]",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,34 +25,31 @@
       "special": true
     },
     "3": {
-      "content": "[MASK]",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "39979": {
-      "content": "[UNK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "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,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c7d45dfd29b98d96f7df2e8c5345c95546549e178fe1bb79a7a1e44c911873
+oid sha256:21cae3454354b553717895b09df57ca75ec5b2efa49b0d1edcd96b0d86771699
 size 5344