models2.json: use ChatML for Mistral OpenOrca #1935
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
manyoso
approved these changes
Feb 6, 2024
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Member
Author
|
I tweaked the system prompt for more friendly output: |
dpsalvatierra
pushed a commit
to dpsalvatierra/gpt4all
that referenced
this pull request
Feb 16, 2024
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR fixes the output of Mistral OpenOrca for a user prompt such as:
Before, the model would be likely to spew random things in Dutch endlessly, and get stuck in a repetitive loop. Using ChatML makes the model behave much more like a personal assistant.
Before:
Details
After:
Details
This system prompt encourages chain-of-thought style responses, which likely improves the model's problem-solving skills, but is perhaps not a good default for a friendly model for the user to have a conversation with?