Upload tokenizer

special_tokens_map.json

@@ -1,4 +1,27 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": true,
@@ -13,18 +36,6 @@
     "rstrip": true,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|dummy_87|>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "�",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|im_end|>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -8,15 +8,6 @@
   },
   "padding": null,
   "added_tokens": [
-    {
-      "id": 5809,
-      "content": "�",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
     {
       "id": 100256,
       "content": "<|dummy_0|>",
@@ -93,8 +84,8 @@
       "id": 100264,
       "content": "<|im_start|>",
       "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
+      "lstrip": false,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -102,8 +93,8 @@
       "id": 100265,
       "content": "<|im_end|>",
       "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
+      "lstrip": false,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -111,8 +102,8 @@
       "id": 100266,
       "content": "<|im_sep|>",
       "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
+      "lstrip": false,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },

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,
@@ -75,25 +67,25 @@
     },
     "100264": {
       "content": "<|im_start|>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "100265": {
       "content": "<|im_end|>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "100266": {
       "content": "<|im_sep|>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -778,14 +770,18 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_sep|>",
+    "<|im_end|>"
+  ],
   "bos_token": "<|endoftext|>",
   "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_max_length": 16384,
-  "pad_token": "<|dummy_87|>",
-  "padding_side": "right",
+  "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "�"
+  "unk_token": "<|endoftext|>"
 }