Upload tokenizer

special_tokens_map.json

@@ -1,4 +1,10 @@
 {
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -13,7 +19,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -25,19 +25,59 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "use_fast": true
+  "use_default_system_prompt": false
 }