Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
+}

special_tokens_map.json

@@ -1,30 +1,19 @@
 {
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
   "bos_token": {
-    "content": "<s>",
+    "content": "<|im_start|>",
     "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": "</s>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<|im_end|>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -29,6 +29,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32001,
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -53,7 +71,7 @@
     "single": [
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 0
         }
       },
@@ -67,7 +85,7 @@
     "pair": [
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 0
         }
       },
@@ -79,7 +97,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 1
         }
       },
@@ -91,13 +109,13 @@
       }
     ],
     "special_tokens": {
-      "<s>": {
-        "id": "<s>",
+      "<|im_start|>": {
+        "id": "<|im_start|>",
         "ids": [
-          1
+          32000
         ],
         "tokens": [
-          "<s>"
+          "<|im_start|>"
         ]
       }
     }

tokenizer_config.json

@@ -25,24 +25,37 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
-  "bos_token": "<s>",
+  "additional_special_tokens": [],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "padding_side": "left",
+  "pad_token": "<|im_end|>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "split_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": true,
+  "use_fast": true
 }