Upload tokenizer

special_tokens_map.json

@@ -16,5 +16,11 @@
     "<start_assistant>",
     "<end_message>"
   ],
-  "eos_token": "<end_message>"
+  "eos_token": {
+    "content": "<end_message>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -5,147 +5,147 @@
   "added_tokens": [
     {
       "id": 0,
-      "special": true,
       "content": ">>TITLE<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 1,
-      "special": true,
       "content": ">>ABSTRACT<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 2,
-      "special": true,
       "content": ">>INTRODUCTION<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 3,
-      "special": true,
       "content": ">>SUMMARY<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 4,
-      "special": true,
       "content": ">>COMMENT<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 5,
-      "special": true,
       "content": ">>ANSWER<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 6,
-      "special": true,
       "content": ">>QUESTION<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 7,
-      "special": true,
       "content": ">>DOMAIN<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 8,
-      "special": true,
       "content": ">>PREFIX<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 9,
-      "special": true,
       "content": ">>SUFFIX<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 10,
-      "special": true,
       "content": ">>MIDDLE<<",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 11,
-      "special": true,
       "content": "<|endoftext|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
-      "id": 65023,
-      "special": true,
-      "content": "<start_system>",
+      "id": 65020,
+      "content": "<end_message>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
-      "id": 65022,
-      "special": true,
-      "content": "<start_user>",
+      "id": 65021,
+      "content": "<start_assistant>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
-      "id": 65021,
-      "special": true,
-      "content": "<start_assistant>",
+      "id": 65022,
+      "content": "<start_user>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
-      "id": 65020,
-      "special": true,
-      "content": "<end_message>",
+      "id": 65023,
+      "content": "<start_system>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,
@@ -159,7 +159,8 @@
       {
         "type": "ByteLevel",
         "add_prefix_space": false,
-        "trim_offsets": true
+        "trim_offsets": true,
+        "use_regex": true
       },
       {
         "type": "Digits",
@@ -179,7 +180,8 @@
   "decoder": {
     "type": "ByteLevel",
     "add_prefix_space": true,
-    "trim_offsets": true
+    "trim_offsets": true,
+    "use_regex": true
   },
   "model": {
     "type": "BPE",
@@ -188,6 +190,7 @@
     "continuing_subword_prefix": null,
     "end_of_word_suffix": null,
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       ">>TITLE<<": 0,
       ">>ABSTRACT<<": 1,

tokenizer_config.json

@@ -1,7 +1,155 @@
 {
   "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65020": {
+      "content": "<end_message>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65021": {
+      "content": "<start_assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65022": {
+      "content": "<start_user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65023": {
+      "content": "<start_system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<",
+    "<start_system>",
+    "<start_user>",
+    "<start_assistant>",
+    "<end_message>"
+  ],
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<start_user>' + message['content'].strip() + '<end_message>' }}{% elif message['role'] == 'system' %}{{ '<start_system>' + message['content'].strip() + '<end_message>' }}{% elif message['role'] == 'assistant' %}{{ '<start_asssistant>'  + message['content'] + '<end_message>' }}{% else %}{{ raise_exception('Only system, user and assistant roles are supported.') }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<start_asssistant>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<end_message>",
   "model_max_length": 8192,
-  "special_tokens_map_file": null,
   "tokenizer_class": "PreTrainedTokenizerFast"
 }