Upload tokenizer

special_tokens_map.json

@@ -9,11 +9,5 @@
   "mask_token": "<MASK>",
   "pad_token": "<PAD>",
   "sep_token": "<SEP>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -116,7 +116,7 @@
     "single": [
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 0
         }
       },
@@ -130,7 +130,7 @@
     "pair": [
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 0
         }
       },
@@ -142,7 +142,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<s>",
+          "id": "<|im_start|>",
           "type_id": 1
         }
       },
@@ -154,13 +154,13 @@
       }
     ],
     "special_tokens": {
-      "<s>": {
-        "id": "<s>",
+      "<|im_start|>": {
+        "id": "<|im_start|>",
         "ids": [
-          1
+          32005
         ],
         "tokens": [
-          "<s>"
+          "<|im_start|>"
         ]
       }
     }

tokenizer_config.json

@@ -1,34 +1,103 @@
 {
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
+  "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": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<EOD>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "<MASK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "<CLS>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
+  "mask_token": "<MASK>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "<PAD>",
   "padding_side": "right",
+  "sep_token": "<SEP>",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "unk_token": "<unk>",
   "use_default_system_prompt": false
 }