Upload tokenizer

chat_template.jinja

@@ -3,7 +3,7 @@
     {%- if messages[0]['role'] == 'system' %}
         {{- messages[0]['content'] }}
     {%- else %}
-        {{- 'You are a helpful assistant.' }}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
     {%- endif %}
     {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
     {%- for tool in tools %}
@@ -15,7 +15,7 @@
     {%- if messages[0]['role'] == 'system' %}
         {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
     {%- else %}
-        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- for message in messages %}

special_tokens_map.json

@@ -15,7 +15,7 @@
     "<|video_pad|>"
   ],
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -196,10 +196,10 @@
   ],
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",