Upload tokenizer

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: duraad/nep-spell-mbart-new
 tags:
 - generated_from_trainer
 metrics:
@@ -7,6 +6,7 @@ metrics:
 - precision
 - recall
 - f1
+base_model: duraad/nep-spell-mbart-new
 model-index:
 - name: nep-spell-mbart-new
   results: []

special_tokens_map.json

@@ -53,9 +53,27 @@
     "gl_ES",
     "sl_SI"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -63,7 +81,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0742c8f849b4108e1b2d0e5ca109391cf86da0f8f9462d85ad2f9f7d97bf4cbf
-size 17110208
+oid sha256:a17faaf4d244b98f7b82cd97cc65088c2815c9375de600529f7f7634da093ab6
+size 17094857

tokenizer_config.json

@@ -516,12 +516,19 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 1024,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
   "src_lang": "ne_NP",
+  "stride": 0,
   "tgt_lang": "ne_NP",
   "tokenizer_class": "MBart50Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }