Update tokenizer_config.json

tokenizer_config.json

@@ -1,9 +1,18 @@
 {
   "add_bos_token": true,
-  "add_prefix_space": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "1": {
-      "content": "<pad>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -19,23 +28,17 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<pad>",
-    "</s>"
-  ],
-  "bos_token": "</s>",
-  "clean_up_tokenization_spaces": true,
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "errors": "replace",
-  "max_length": 512,
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "stride": 0,
-  "tokenizer_class": "GPT2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "</s>"
-}
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}