Upload tokenizer

special_tokens_map.json

@@ -1,4 +1,41 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
@@ -6,20 +43,8 @@
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<PAD>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "pad_token": "<PAD>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -230,12 +230,12 @@
     },
     {
       "id": 50277,
-      "content": "<|im_start|>",
+      "content": "<|START_OF_TURN_TOKEN|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
-      "special": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 50278,
@@ -243,12 +243,30 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
       "id": 50279,
-      "content": "<|im_end|>",
+      "content": "<|USER_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50280,
+      "content": "<|CHATBOT_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50281,
+      "content": "<|END_OF_TURN_TOKEN|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -266,10 +284,30 @@
     "use_regex": true
   },
   "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": false,
-    "trim_offsets": true,
-    "use_regex": true
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
   },
   "decoder": {
     "type": "ByteLevel",
@@ -285,6 +323,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<|padding|>": 1,

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": false,
+  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
@@ -202,23 +204,39 @@
       "special": false
     },
     "50277": {
-      "content": "<|im_start|>",
+      "content": "<|START_OF_TURN_TOKEN|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "50278": {
       "content": "<PAD>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "50279": {
-      "content": "<|im_end|>",
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "<|END_OF_TURN_TOKEN|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -226,15 +244,18 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|START_OF_TURN_TOKEN|>",
+    "<PAD>",
+    "<|USER_TOKEN|>",
+    "<|CHATBOT_TOKEN|>",
+    "<|END_OF_TURN_TOKEN|>"
+  ],
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|im_end|>",
-  "max_length": 1024,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<PAD>",
-  "stride": 0,
   "tokenizer_class": "GPTNeoXTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }