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

feat: Add GLHF Models Provider Integration #502

Conversation

ThePsyberSleuth
Copy link

PR Description

This PR adds support for GLHF Models to the oTToDev platform.

Changes

  • Added GLHF Models provider configuration in constants.ts
  • Updated README.md to include GLHF Models in the supported providers list
  • Fixed TypeScript and linting issues in action-runner.ts
  • Added proper error handling for GLHF API integration
  • Added comprehensive documentation for GLHF Models setup and usage

Documentation Updates

  • Added GLHF Models to the list of supported providers in index.md
  • Added detailed GLHF Models description and setup instructions in CONTRIBUTING.md
  • Added environment variable documentation for GLHF API key

GLHF Models Overview

GLHF.chat is a powerful and flexible LLM service that enables users to run virtually any Hugging Face model with minimal setup. The service features:

  • Universal support for Hugging Face models
  • Advanced GPU infrastructure with up to 8 Nvidia H100 80GB GPUs
  • Custom GPU scheduler with vLLM technology
  • Automatic resource provisioning and scaling
  • Model fine-tuning capabilities
  • Cost-effective multi-tenant infrastructure

Testing

  • Verified GLHF Models appear in the provider selection
  • Tested API integration with proper error handling
  • Ensured TypeScript types are properly maintained
  • Confirmed all linting rules pass

Requires

  • GLHF_API_KEY environment variable for accessing GLHF Models

Contributors

Related Issues

None

- Implement GitHub Models provider using Azure ML endpoints
- Add comprehensive model selection including Llama, Mistral, GPT-4O, and Phi series
- Add documentation for the provider in CONTRIBUTING.md
- Configure OpenAI-compatible interface for Azure ML integration
- Fix linting issues in action-runner.ts

Contributed-by: ThePsyberSleuth
- Restore original action execution flow
- Add eslint-disable for consistent-return
- Maintain proper error handling
- Restore original action execution flow
- Add eslint-disable for consistent-return
- Maintain proper error handling
- Implement GLHF.chat provider with Hugging Face model support
- Add dynamic model loading and GPU scheduling integration
- Configure multi-tenant infrastructure support
- Add comprehensive documentation
- Support model fine-tuning and 4-bit quantization

Contributed-by: ThePsyberSleuth
@dustinwloring1988 dustinwloring1988 added enhancement New feature or request and removed enhancement New feature or request labels Dec 2, 2024
@dustinwloring1988
Copy link
Collaborator

@ThePsyberSleuth is this a dub if so please close one: #485

@dustinwloring1988 dustinwloring1988 added enhancement New feature or request model-provider This is a model provider addition labels Dec 2, 2024
@ThePsyberSleuth
Copy link
Author

@ThePsyberSleuth is this a dub if so please close one: #485

Hi @dustinwloring1988 please can you explain to me what you're talking about as this is my first time contributing to a project.

@dustinwloring1988
Copy link
Collaborator

please see this link: #485

@ThePsyberSleuth
Copy link
Author

please see this link: #485

Thanks @dustinwloring1988 just closed the other PR

@dustinwloring1988
Copy link
Collaborator

@ThePsyberSleuth please fix the conflicts so we can look at it

@ThePsyberSleuth
Copy link
Author

@ThePsyberSleuth please fix the conflicts so we can look at it

@dustinwloring1988 Just resolved all conflicts please review

@akrmba
Copy link

akrmba commented Dec 3, 2024

Thanks

@ThePsyberSleuth
Copy link
Author

Thanks

Most welcome

@dustinwloring1988
Copy link
Collaborator

Thanks for the update but in the drop down for the provider it show 2 (GitHub Models and GLHF, is this intended):
11

@ThePsyberSleuth
Copy link
Author

ThePsyberSleuth commented Dec 6, 2024

Thanks for the update but in the drop down for the provider it show 2 (GitHub Models and GLHF, is this intended):
11

Yes, I added the Github provider first but merge the branch with the glhf.

Like I said it is my first time contributing. I don't know if it is a problem or not.

@ThePsyberSleuth ThePsyberSleuth closed this by deleting the head repository Dec 11, 2024
@andreclemente
Copy link

Hey, was this pull request merged? I think we're still missing GLHF

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request model-provider This is a model provider addition
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants