Upload tokenizer_config.json

tokenizer_config.json

@@ -227,9 +227,11 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "clean_up_tokenization_spaces": false,
+  "chat_template": "{%- if tools %}\n<|im_start|>system\n{%- if messages[0].role == 'system' %}\n{{ messages[0].content }}\n\n{%- endif %}\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 %}\n{{ tool | tojson }}{%- endfor %}\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{%- else %}{%- if messages[0].role == 'system' %}\n<|im_start|>system\n{{ messages[0].content }}<|im_end|>\n{%- endif %}{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}{%- set index = (messages|length - 1) - loop.index0 %}{%- set message = messages[index] %}{%- set current_content = message.content if message.content is not none else '' %}{%- set tool_start = '<tool_response>' %}{%- set tool_start_length = tool_start|length %}{%- set start_of_message = current_content[:tool_start_length] %}{%- set tool_end = '</tool_response>' %}{%- set tool_end_length = tool_end|length %}{%- set start_pos = (current_content|length) - tool_end_length %}{%- if start_pos < 0 %}{%- set start_pos = 0 %}{%- endif %}{%- set end_of_message = current_content[start_pos:] %}{%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}{%- set ns.multi_step_tool = false %}{%- set ns.last_query_index = index %}{%- endif %}{%- endfor %}\n{%- for message in messages %}{%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}<|im_start|>{{ message.role }}\n{{ message.content }}<|im_end|>\n{%- elif message.role == \"assistant\" %}<|im_start|>assistant\n{%- if message.content %}{{ message.content }}{%- endif %}{%- if message.tool_calls %}{%- for tool_call in message.tool_calls %}{%- if (loop.first and content) or (not loop.first) %}\n{%- endif %}{%- if tool_call.function %}{%- set tool_call = tool_call.function %}{%- endif %}<tool_call>\n{\"name\": \"{{ tool_call.name }}\", \"arguments\": {{ tool_call.arguments if tool_call.arguments is string else tool_call.arguments | tojson }}}\n</tool_call>{%- endfor %}{%- endif %}<|im_end|>\n{%- elif message.role == \"tool\" %}{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}<|im_start|>user{%- endif %}\n<tool_response>\n{{ message.content }}\n</tool_response>{%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}<|im_end|>\n{%- endif %}{%- endif %}{%- endfor %}\n{%- if add_generation_prompt %}<|im_start|>assistant\n{%- endif %}",
+
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "clean_up_tokenization_spaces": false,
   "extra_special_tokens": {},
   "model_max_length": 40960,
   "pad_token": "<|vision_pad|>",
@@ -237,4 +239,4 @@
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null
-}
+}