Skip to content
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

Default to merge_system_user_message if mistral model detected #100

Merged
merged 1 commit into from
Aug 19, 2024

Conversation

danmcp
Copy link
Member

@danmcp danmcp commented Aug 15, 2024

Resolves: #97

Requires #98 to be able to function but won't cause any harm to merge before.

Signed-off-by: Dan McPherson <dmcphers@redhat.com>
@danmcp
Copy link
Member Author

danmcp commented Aug 15, 2024

@JamesKunstle FYI

@@ -254,7 +254,7 @@ def chat_completion_openai(
try:
messages = conv.to_openai_api_messages()
if (
merge_system_user_message
(merge_system_user_message or conv.name == "mistral")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely solved for mistral (and mixtral). I wonder if there are other models that disallow system messages. If so, we could enum the names and extend that list. This patch is perfect as is though- just food for thought.

@danmcp danmcp merged commit 515263a into instructlab:main Aug 19, 2024
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Auto detect mixtral type judge models and auto set merge_system_user_message
3 participants