add tokenizer

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ Ø
 Û Į
 Ø §

special_tokens_map.json

@@ -1,7 +1,5 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,33 +1,7 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "name_or_path": "hadidev/gpt2-urdu-tokenizer",
-  "pad_token": null,
-  "special_tokens_map_file": "/root/.cache/huggingface/transformers/fd05696fd7c524ed400d964c4d1fa66c6435bc0d588c55f7ac98c7c850c7cc5a.b7f8742f1d370b815979aeabc401aed45c79760724667d2725ac7503c242b97f",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

vocab.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab6656bcf981ae51e1548a3879bf0ddc1167b1605dbaaccb71c7dcb5f8240e31
-size 10897434
+oid sha256:2e6a8e0b20ac6772046974b5e3f8998106d98de43dad56aa82f2552754875006
+size 9733956