Files
Qwen3-Lite-3B-0.9B/candidate_v1_smoke_suite.json
ModelHub XC 8871922bf3 初始化项目,由ModelHub XC社区提供模型
Model: refinefuture-ai/Qwen3-Lite-3B-0.9B
Source: Original Platform
2026-06-13 17:21:23 +08:00

51 lines
1.9 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

[
{
"id": "intro",
"prompt": "你好,请简单介绍一下你自己。",
"expectation": "能够给出自然、简短的中文自我介绍。",
"response": "你好,我可以回答问题、解释概念,也可以先去这个问题。"
},
{
"id": "capability",
"prompt": "你会做什么?请简短回答。",
"expectation": "能够简洁说明回答问题、整理信息等基础能力。",
"response": "我可以回答问题、整理信息,并给出简短说明。"
},
{
"id": "arithmetic",
"prompt": "1加1等于几",
"expectation": "能够直接回答 2。",
"response": "2。"
},
{
"id": "comfort",
"prompt": "如果我说我今天有点累,你会怎么回复?",
"expectation": "能够给出自然、简短的安抚式回复。",
"response": "先别急,慢慢说,我会尽量帮你理清楚。"
},
{
"id": "moe_explain",
"prompt": "请用一句话解释什么是混合专家模型。",
"expectation": "能够用一句中文解释 MoE 的稀疏激活特性。",
"response": "混合专家模型是在一次计算中只激活部分专家网络,从而降低计算成本。"
},
{
"id": "encourage",
"prompt": "请给我一句鼓励的话。",
"expectation": "能够生成完整自然的鼓励语句,不出现重复或残句。",
"response": "别着急,慢慢说,也能让一点简单一点一点。"
},
{
"id": "soothe",
"prompt": "请给我一句安慰的话。",
"expectation": "能够生成完整自然的安慰语句,不出现重复或病句。",
"response": "你已经在往前走了,但还可以帮助你去。"
},
{
"id": "closing",
"prompt": "请给出一句正常的结束语。",
"expectation": "能够给出自然的中文结束语。",
"response": "如果你愿意,我可以继续帮你处理下一个问题。"
}
]