the chat input format is not right

[moseshu]

I start vllm server with OpenAI-API-compatible,

url="http://localhost:v1"

the below picture is my input. I check the vllm log,there is no assistant text ,only has "Final Answer:"? why?

the vllm log is

prompt: '<s>[INST] <<SYS>>\nRespond to the human as helpfully and accurately as possible. \n\n\n\nYou have access to the following tools:\n\n[]\n\nUse a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).\nValid "action" values: "Final Answer" or \n\nProvide only ONE action per $JSON_BLOB, as shown:\n\n```\n{\n  "action": $TOOL_NAME,\n  "action_input": $ACTION_INPUT\n}\n```\n\nFollow this format:\n\nQuestion: input question to answer\nThought: consider previous and subsequent steps\nAction:\n```\n$JSON_BLOB\n```\nObservation: action result\n... (repeat Thought/Action/Observation N times)\nThought: I know what to respond\nAction:\n```\n{\n  "action": "Final Answer",\n  "action_input": "Final response to human"\n}\n```\n\nBegin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.\n\n<</SYS>>\n\n你在哪呢 [/INST]  Final Answer: </s><s>[INST] 爱你哦 [/INST] '

[patryk20120]

Can you specify a little bit more for non Chinese audience?