add <|func_start|>

added_tokens.json

@@ -1,6 +1,4 @@
 {
-  "</s>": 2,
-  "<s>": 1,
-  "<unk>": 0,
-  "<|func_end|>": 36128
+  "<|func_end|>": 36128,
+  "<|func_start|>": 36129
 }

special_tokens_map.json

@@ -4,8 +4,32 @@
     "<s>",
     "</s>"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<unk>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -38,6 +38,15 @@
       "rstrip": true,
       "normalized": false,
       "special": false
+    },
+    {
+      "id": 36129,
+      "content": "<|func_start|>",
+      "single_word": true,
+      "lstrip": true,
+      "rstrip": true,
+      "normalized": false,
+      "special": false
     }
   ],
   "normalizer": {
@@ -97525,4 +97534,4 @@
       "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
     ]
   }
-}
+}

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -31,6 +33,14 @@
       "rstrip": true,
       "single_word": true,
       "special": false
+    },
+    "36129": {
+      "content": "<|func_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": false
     }
   },
   "additional_special_tokens": [