官方demo运行正常，本地运行跟个傻子一样，请问怎么回事？
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 40.3k
- Forks
- 3.7k
- PR merge metrics
- No merged PRs in 30d
Description
测试了 1B 3B 7B 10B 和 基础模型 2B 回答都不好。
{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"地球与月球的平均距离约为238,000千米。","role":"assistant"}}],"created":1773824825,"model":"gpt-3.5-turbo-0613","object":"chat.completion","usage":{"completion_tokens":26,"prompt_tokens":127,"total_tokens":153},"id":"chatcmpl-bZVssHWGmXJxuvEmjJU4F3Nm8In8Q4xd"}
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the reported difference between the official demo and the local run using the listed 1B, 2B, 3B, 7B, and 10B models. Read the repository's local inference instructions and compare the local configuration with the demo; done means identifying a reproducible cause or documenting the missing environment details needed to explain the poor answers.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100