Skip to content

Default to merge_system_user_message if mistral model detected #100

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.

Sign up for GitHub

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

Merged
danmcp merged 1 commit into from
Aug 19, 2024
Merged

Default to merge_system_user_message if mistral model detected #100

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/instructlab/eval/mt_bench_common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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")

@JamesKunstle JamesKunstle Aug 17, 2024

Copy link
Copy Markdown
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.

and messages[0]["role"] == "system"
and messages[1]["role"] == "user"
):
Expand Down