Upload tokenizer

special_tokens_map.json

@@ -1,30 +1,19 @@
 {
   "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
     "▁<EOT>"
   ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "</s>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -9,7 +9,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -18,7 +18,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -34,8 +34,8 @@
       "id": 32000,
       "content": "▁<PRE>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -43,8 +43,8 @@
       "id": 32001,
       "content": "▁<MID>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -52,8 +52,8 @@
       "id": 32002,
       "content": "▁<SUF>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -61,8 +61,8 @@
       "id": 32003,
       "content": "▁<EOT>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     }

tokenizer_config.json

@@ -1,4 +1,62 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "▁<PRE>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "▁<MID>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "▁<SUF>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "▁<EOT>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
   "additional_special_tokens": [
     "▁<PRE>",
     "▁<MID>",
@@ -13,23 +71,9 @@
     "▁<SUF>",
     "▁<EOT>"
   ],
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "</s>",
   "eot_token": "▁<EOT>",
   "fill_token": "<FILL_ME>",
   "legacy": null,
@@ -40,13 +84,6 @@
   "sp_model_kwargs": {},
   "suffix_token": "▁<SUF>",
   "tokenizer_class": "CodeLlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "unk_token": "<unk>",
   "use_default_system_prompt": false
 }