Add support for Mistral models via Bedrock #400
Merged
Conversation
This file contains 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
fixes to the LLama2 and mistral prompts
| @@ -33,7 +29,9 @@ def prepare_input( | |||
| if provider == "anthropic": | |||
There was a problem hiding this comment.
should we move model providers to enum?
bigadsoleiman
approved these changes
Mar 7, 2024
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Outdated suggestions cannot be applied.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.
Issue #, if available:
Resolves: #390
Description of changes:
Given that the prompt format of Mistral and Mixtral are identical to Llama2, we reused the Llama2 adapter registering it also for Mistral models
The input and output adaptations are different and taken care by the base Bedrock LLM class
Finally, we revised the LLama2 prompts.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.