We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Originally posted by ReycoLi December 19, 2024 数据集的格式如下
"messages": [ { "role": "system", "content": "agent职责..." }, { "role": "user", "content": "用户实际问题" }, { "role": "assistant", "content": "Thought:...\n Action: ...\n Observation:..." } ]
assistant回复中只有Thought和Action部分去计算loss,Observation部分不参与loss计算。 该如何实现这个功能,基于llama factory框架的最佳实践应该是什么,修改哪部分的代码。
求大神指点。
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Discussed in #6389
Originally posted by ReycoLi December 19, 2024
数据集的格式如下
"messages": [
{
"role": "system",
"content": "agent职责..."
},
{
"role": "user",
"content": "用户实际问题"
},
{
"role": "assistant",
"content": "Thought:...\n Action: ...\n Observation:..."
}
]
assistant回复中只有Thought和Action部分去计算loss,Observation部分不参与loss计算。
该如何实现这个功能,基于llama factory框架的最佳实践应该是什么,修改哪部分的代码。
求大神指点。
The text was updated successfully, but these errors were encountered: