update model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli",
+  "_name_or_path": "./mdeberta-ner",
   "architectures": [
     "DebertaV2ForTokenClassification"
   ],
@@ -8,20 +8,20 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4"
+    "0": "O",
+    "1": "LOC",
+    "2": "PER",
+    "3": "MISC",
+    "4": "ORG"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4
+    "LOC": 1,
+    "MISC": 3,
+    "O": 0,
+    "ORG": 4,
+    "PER": 2
   },
   "layer_norm_eps": 1e-07,
   "legacy": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a83bb13755d4a3791303df600d054b18bb67e2644931c2d92efb84b23d871b49
+oid sha256:fa4d19bbd3c0d91d0f6a0874b0d19cc32f91d00f1ca3aac13e78496ac16e3472
 size 1112914884

special_tokens_map.json

@@ -44,7 +44,7 @@
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c405b11c22d1def92c599a77ffa8a37b2f7d35654651510aa834cd2d54d5328
-size 16316126
+oid sha256:da06fa6bca6c8ccbd98d524d3baaa25a9e0f8690d9d31e52f72e1fed685ae465
+size 16316380

tokenizer_config.json

@@ -27,7 +27,7 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -42,18 +42,25 @@
     }
   },
   "bos_token": "[CLS]",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "eos_token": "[SEP]",
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},
   "split_by_punct": false,
+  "stride": 0,
   "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]",
   "vocab_type": "spm"
 }