-
Notifications
You must be signed in to change notification settings - Fork 139
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
推理不能正常输出 #380
Comments
..... 泥为啥觉得 7B 换 1.5B 是合理的呢... 俺不管广告怎么宣传,2024年通用对话业务就是不能用 10B 以下的模型。 如果没有合适的机器, config.ini 用 siliconcloud, 例如 remote_type = "siliconcloud"
# 你的 siliconcloud token 写这里
remote_api_key = "YOUR-API-KEY-HERE"
remote_llm_max_text_length = 40000
# see https://siliconflow.readme.io/reference/chat-completions-1
# 你想用的模型名字,挑个大的
remote_llm_model = "YOUR-MODEL-NAME" |
已调整默认模型配置,现在应该是可以的。 |
不涉及业务合理性,主要是7B模型本机运行OOM,所以想1.5B模型先跑通再做其他考量 |
我该如何处理,重新clone repo本机运行,或者选择siliconcloud? |
选择 siliconcloud,“听起来” 你那边没合适机器 |
detail | 详细描述 | 詳細な説明
按照文档完成vector store的创建,之后运行python3 -m huixiangdou.main --standalone,输出如上图所示,看起来是模型认为query与vector store存储的信息毫无关系。
运行python3 -m huixiangdou.main --standalone与文档的不同操作在于,修改了config.ini中的internLM 7B到1.5B,其他地方未做任何修改,请大神指点如何操作。
The text was updated successfully, but these errors were encountered: