kaki-paper commited on
Commit
8a355f6
·
verified ·
1 Parent(s): 8c1f5da

Update tokenizer_config.json

Browse files

fixes this error:

Traceback (most recent call last):
File "/data/workspace/howard/workspace/LLaVA-NeXT/qwen2_vl_test_inference.py", line 35, in <module>
prompt = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
File "/data/workspace/howard/workspace/.visionzip_test/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1774, in apply_chat_template
compiled_template = self._compile_jinja_template(chat_template)
File "/data/workspace/howard/workspace/.visionzip_test/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1835, in _compile_jinja_template
return jinja_env.from_string(chat_template)
File "/data/workspace/howard/workspace/.visionzip_test/lib/python3.10/site-packages/jinja2/environment.py", line 1108, in from_string
return cls.from_code(self, self.compile(source), gs, None)
File "/data/workspace/howard/workspace/.visionzip_test/lib/python3.10/site-packages/jinja2/environment.py", line 768, in compile
self.handle_exception(source=source_hint)
File "/data/workspace/howard/workspace/.visionzip_test/lib/python3.10/site-packages/jinja2/environment.py", line 939, in handle_exception
raise rewrite_traceback_stack(source=source)
File "<unknown>", line 7, in template
jinja2.exceptions.TemplateSyntaxError: Encountered unknown tag 'generation'. Jinja was looking for the following tags: 'endfor' or 'else'. The innermost block that needs to be closed is 'for'.

fixed chat template came from NCSOFT/VARCO-VISION-14B-HF

Files changed (1) hide show
  1. tokenizer_config.json +1 -1
tokenizer_config.json CHANGED
@@ -271,7 +271,7 @@
271
  "<delim>"
272
  ],
273
  "bos_token": null,
274
- "chat_template": "{% if messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' }}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{ '<|im_end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
275
  "pad_token": "[UNK]",
276
  "padding_side": "right",
277
  "split_special_tokens": false,
 
271
  "<delim>"
272
  ],
273
  "bos_token": null,
274
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
275
  "pad_token": "[UNK]",
276
  "padding_side": "right",
277
  "split_special_tokens": false,