Update ChatBedrock for Llama 4 model support #475
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
3coins
reviewed
May 29, 2025
| def _convert_one_message_to_text_llama4(message: BaseMessage) -> str: | ||
| if isinstance(message, ChatMessage): | ||
| message_text = ( | ||
| f"<|header_start|>{message.role}<|header_end|>{message.content}<|eot|>" |
There was a problem hiding this comment.
Are arbitrary roles supported?
https://www.llama.com/docs/model-cards-and-prompt-formats/llama4/#-llama-4---prompt-formats-
There was a problem hiding this comment.
That's a good point, I'm honestly not too sure.
This is in line with the llama3 ChatMessage translator implementation, where the model also does not explicitly support arbitrary roles. But in practice, at worst, llama3 and llama4 seem to ignore the custom role.
3coins
approved these changes
May 30, 2025
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Outdated suggestions cannot be applied.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.
Updating ChatBedrock to correctly format prompts for Llama 4 models, following the official documentation:
https://www.llama.com/docs/model-cards-and-prompt-formats/llama4/