Skip to content

Default to merge_system_user_message if mistral model detected#100

Merged
danmcp merged 1 commit into
instructlab:mainfrom
danmcp:mergesystemusermessage
Aug 19, 2024
Merged

Default to merge_system_user_message if mistral model detected#100
danmcp merged 1 commit into
instructlab:mainfrom
danmcp:mergesystemusermessage

Conversation

@danmcp

@danmcp danmcp commented Aug 15, 2024

Copy link
Copy Markdown
Contributor

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

danmcp commented Aug 15, 2024

Copy link
Copy Markdown
Contributor Author

@JamesKunstle FYI

messages = conv.to_openai_api_messages()
if (
merge_system_user_message
(merge_system_user_message or conv.name == "mistral")

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.

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