Upload tokenizer

special_tokens_map.json

@@ -1,3 +1,5 @@
 {
+  "bos_token": "<|begin_of_sequence|>",
+  "eos_token": "<|end_of_sequence|>",
   "pad_token": "<|pad|>"
 }

tokenizer.json

@@ -5,7 +5,7 @@
   "added_tokens": [
     {
       "id": 0,
-      "content": "<|im_start|>",
+      "content": "<|begin_of_sequence|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -14,7 +14,7 @@
     },
     {
       "id": 1,
-      "content": "<|im_sep|>",
+      "content": "<|end_of_sequence|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "<|start_bytes|>",
+      "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -32,7 +32,7 @@
     },
     {
       "id": 3,
-      "content": "<|end_bytes|>",
+      "content": "<|im_sep|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -95,10 +95,10 @@
     "fuse_unk": false,
     "byte_fallback": false,
     "vocab": {
-      "<|im_start|>": 0,
-      "<|im_sep|>": 1,
-      "<|start_bytes|>": 2,
-      "<|end_bytes|>": 3,
+      "<|begin_of_sequence|>": 0,
+      "<|end_of_sequence|>": 1,
+      "<|im_start|>": 2,
+      "<|im_sep|>": 3,
       "<|im_end|>": 4,
       "<|semantic|>": 5,
       "<|pad|>": 6,

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<|im_start|>",
+      "content": "<|begin_of_sequence|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<|im_sep|>",
+      "content": "<|end_of_sequence|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "<|start_bytes|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "<|end_bytes|>",
+      "content": "<|im_sep|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -57,7 +57,9 @@
       "special": true
     }
   },
+  "bos_token": "<|begin_of_sequence|>",
   "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_sequence|>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|pad|>",
   "tokenizer_class": "PreTrainedTokenizerFast"