-
Notifications
You must be signed in to change notification settings - Fork 25
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
自建model请求token超出 #12
Comments
我没创建过自己的model,所以不太清楚 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
使用自己的训练库文件,片段:{"prompt":"什么汤最鲜->","completion":" 鱼羊汤,因为鱼羊一鲜\nENDEND"},创建一个model。
调用的时候:
CompletionReq req = CompletionReq.builder().model("curie:ft-personal-2023-04-06-09-02-34").prompt("什么汤最鲜").stop("\nENDEND").build();
CompletionRes res = service.completions(req);
返回:
"error": {
"message": "This model's maximum context length is 2049 tokens, however you requested 2060 tokens (12 in your prompt; 2048 for the completion). Please reduce your prompt; or completion length.",
"type": "invalid_request_error",
"param": null,
"code": null
}
加了max_token,就强行把答案补充到max_token的长度,最后一个文字一直重复,不能正常对话,不加max_token,就一直报这个错。有遇到同样问题的吗?
The text was updated successfully, but these errors were encountered: