arrafmousa
/

gpt2_encoder

Feature Extraction

Model card Files Files and versions

arrafmousa commited on Feb 4, 2025

Commit

c0e6b5c

·

verified ·

1 Parent(s): e341233

Upload tokenizer

Files changed (2) hide show

special_tokens_map.json +1 -7
tokenizer_config.json +1 -9

special_tokens_map.json CHANGED Viewed

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json CHANGED Viewed

@@ -9,14 +9,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "50257": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
@@ -25,7 +17,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 1024,
-  "pad_token": "[PAD]",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }