Skip to content
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.

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

Support for Llama3 via Amazon Bedrock #270

Merged
merged 1 commit into from
May 16, 2024

Conversation

massi-ang
Copy link
Contributor

This PR adds support for Llama3 models via Amazon Bedrock. It also add Anthropic Claude 3 Opus to the list of models.

To avoid referring to hardocded model Id strings in several piece of code, we replaced all hardcoded model Id strings used by Bedrock models with the corresponding NativeLLM enum value.

- added also Claude 3 Opus to the list of models
- replaced hardcoded model Id strings with refs to NativeLLM enum
@ianarawjo
Copy link
Owner

Ok, I’ll get to this in time. Massi, can you check the other issue? Someone had an issue querying Bedrock.

@ianarawjo ianarawjo changed the base branch from main to moremodels May 16, 2024 20:17
@ianarawjo ianarawjo merged commit f227996 into ianarawjo:moremodels May 16, 2024
ianarawjo added a commit that referenced this pull request May 18, 2024
* feat(bedrock_llama3): added support for Llama3 (#270)

- added also Claude 3 Opus to the list of models
- replaced hardcoded model Id strings with refs to NativeLLM enum

* chore: bump @mirai73/bedrock-fm library (#277)

- the new version adds source code to facilitate debugging

Co-authored-by: ianarawjo <fatso784@gmail.com>

* Adding together.ai support (#280)


---------

Co-authored-by: ianarawjo <fatso784@gmail.com>

* Add Together.ai and update Bedrock models

---------

Co-authored-by: Massimiliano Angelino <angmas@amazon.com>
Co-authored-by: Can Bal <canbal@users.noreply.github.com>
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.

None yet

2 participants