fix(tokenizer_config): Sets fim and think tokens to non-special, and removes unk_token.

tokenizer_config.json

@@ -1,14 +1,6 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "5809": {
-      "content": "�",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
     "100256": {
       "content": "<|dummy_0|>",
       "lstrip": true,
@@ -31,7 +23,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "100259": {
       "content": "<|fim_middle|>",
@@ -39,7 +31,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "100260": {
       "content": "<|fim_suffix|>",
@@ -47,7 +39,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "100261": {
       "content": "<|dummy_1|>",
@@ -767,7 +759,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "100351": {
       "content": "</think>",
@@ -775,7 +767,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     }
   },
   "bos_token": "<|endoftext|>",
@@ -786,6 +778,5 @@
   "model_max_length": 32768,
   "pad_token": "<|dummy_85|>",
   "padding_side": "left",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "�"
+  "tokenizer_class": "GPT2Tokenizer"
 }