Correct svg URL, Correct MASK_ID

README.md

@@ -12,7 +12,7 @@ DeBERTaV2 with a short context length to save the memory.
 
 The data set for validation with manual markup consisted of 362 thousand examples.
 
-|![Validation results](https://huggingface.co/fkrasnov2/SBE/blob/main/bvf_recall1k_query_len_eng.svg)|
+|![Validation results](https://huggingface.co/fkrasnov2/SBE/resolve/main/bvf_recall1k_query_len_eng.svg)|
 
 
 ```python
@@ -24,7 +24,7 @@ tokenizer = AutoTokenizer.from_pretrained('fkrasnov2/SBE')
 input_ids = tokenizer.encode("чёрное платье", max_length=model.config.max_position_embeddings, truncation=True, return_tensors='pt')
 
 model.eval()
-vector = model(input_ids=input_ids, attention_mask=input_ids>3)[0][0,0]
+vector = model(input_ids=input_ids, attention_mask=input_ids>tokenizer.mask_token_id)[0][0,0]
 
 assert model.config.hidden_size == vector.shape[0]
 ```

special_tokens_map.json

@@ -3,10 +3,10 @@
   "cls_token": "[CLS]",
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "sep_token": "[SEP]",
   "unk_token": {
-    "content": "[UNK]",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer_config.json

@@ -1,39 +1,39 @@
 {
   "added_tokens_decoder": {
-    "2": {
-      "content": "[CLS]",
+    "0": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[SEP]",
+    "1": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[MASK]",
+    "2": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32000": {
-      "content": "[UNK]",
+    "3": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32001": {
-      "content": "[PAD]",
+    "4": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -48,10 +48,10 @@
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},
   "split_by_punct": false,
   "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }