Upload tokenizer

special_tokens_map.json

@@ -1,9 +1,30 @@
 {
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "<|padding|>"
-  ],
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -202,15 +202,12 @@
       "special": false
     }
   },
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "<|padding|>"
-  ],
   "bos_token": "<|endoftext|>",
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }