feat: Llama 3.1 support, Phi-3 support

[giladgd]

Description of change

• feat: Phi-3 support
• feat: Llama 3.1 support
• feat: model metadata overrides
• feat: use LoRA on a context instead of on a model
• feat: onTextChunk option
• fix: Gemma chat wrapper bug
• fix: GGUF metadata nested key conflicts
• fix: Phi-3 models memory estimation
• fix: adapt to llama.cpp breaking changes
• fix: preserve function calling chunks
• fix: format JSON objects like models expect

Pull-Request Checklist

• Code is up-to-date with the master branch
• npm run format to apply eslint formatting
• npm run test passes with this change
• This pull request links relevant issues as Fixes #0000
• There are new or updated unit tests validating the change
• Documentation has been updated to reflect this change
• The new commits and pull request title follow conventions explained in pull request guidelines (PRs that do not follow this convention will not be merged)

[ido-pluto]

LGTM

[github-actions]

🎉 This PR is included in version 3.0.0-beta.39 🎉

The release is available on:

• v3.0.0-beta.39
• npm package (@beta dist-tag)
• GitHub release
• v3.0.0-beta.39

Your semantic-release bot 📦🚀

[github-actions]

🎉 This PR is included in version 3.0.0 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release
• v3.0.0

Your semantic-release bot 📦🚀