Upload tokenizer

special_tokens_map.json

@@ -1,5 +1,9 @@
 {
   "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
@@ -19,7 +23,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<unk>",
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -60,6 +60,10 @@
     }
   },
   "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
@@ -71,13 +75,20 @@
   "eot_token": "▁<EOT>",
   "fill_token": "<FILL_ME>",
   "legacy": null,
+  "max_length": 512,
   "middle_token": "▁<MID>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<unk>",
+  "pad_to_multiple_of": null,
+  "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
+  "stride": 0,
   "suffix_token": "▁<SUF>",
   "tokenizer_class": "CodeLlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }