[Bug] 使用one-api挂载nvdia的模型nvidia/nemotron-4-340b-instruct时出现报错，而fastgpt可以正常使用

[liuzj288]

📦 部署环境

Docker

📌 软件版本

1.2.14

💻 系统环境

Other Linux

🌐 浏览器

Chrome

🐛 问题描述

1.one-api挂载没问题

2.meta/llama3-70b-instruct使用没有问题，nvidia/nemotron-4-340b-instruct和google/gemma-2-9b-it都报错

3.在fastgpt中可以正常使用

📷 复现步骤

No response

🚦 期望结果

No response

📝 补充信息

No response

[lobehubbot]

👀 @liuzj288

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

📦 Deployment environment

Docker

📌 Software version

1.2.14

💻 System environment

Other Linux

🌐 Browser

Chrome

🐛 Problem description

1.One-api mounting is no problem

2.meta/llama3-70b-instruct works without problems, nvidia/nemotron-4-340b-instruct and google/gemma-2-9b-it both report errors.

3. Can be used normally in fastgpt

📷 Steps to reproduce

No response

🚦 Expected results

No response

📝 Supplementary information

No response

[arvinxx]

你应该去问下 one-api 422 是什么错误吧？

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

You should ask one-api 422 what is the error?

[liuzj288]

你应该去问下 one-api 422 是什么错误吧？

类似这个问题https://github.com/songquanpeng/one-api/issues/1290，看了下回答说是

这个有能设置的地方吗？

[arvinxx]

没有， openai 是支持的，不可能为了三方代理的接口去掉这两个配置。

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

No, openai supports it, and it is impossible to remove these two configurations for the third-party proxy interface.

[lobehubbot]

✅ @liuzj288

This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题，可以留言并回复。