Skip to content
@explodinggradients

Exploding Gradients

README.md

đź‘‹ Hello!

Welcome to Exploding Gradients

Static Badge Static Badge


We are a group of passionate individuals leveraging cutting-edge research and pragmatic engineering practices to empower the visionaries redefining the possibilities of LLMs by providing them with the right tools.

The following are some of the projects we are proud of:

  • Ragas - SOTA metrics for evaluating Retrieval Augmented Generation (RAG) pipelines
  • Funtuner - Supervised instruction finetuning for LLM with HF trainer and Deepspeed
  • Nemesis - Reward Model framework for LLM RLHF

Pinned Loading

  1. ragas ragas Public

    Supercharge Your LLM Application Evaluations 🚀

    Python 7.2k 729

  2. Funtuner Funtuner Public

    Supervised instruction finetuning for LLM with HF trainer and Deepspeed

    Python 34 5

  3. nemesis nemesis Public

    Reward Model framework for LLM RLHF

    Python 58 3

  4. notes notes Public

    Research notes and extra resources for all the work at explodinggradients.com

    Jupyter Notebook 20 5

Repositories

Showing 7 of 7 repositories
  • ragas Public

    Supercharge Your LLM Application Evaluations 🚀

    explodinggradients/ragas’s past year of commit activity
    Python 7,165 Apache-2.0 729 257 14 Updated Nov 8, 2024
  • synthetic-qa-paper Public

    Repo to add code and data for synthetic test data generation

    explodinggradients/synthetic-qa-paper’s past year of commit activity
    Python 0 MIT 1 0 3 Updated Nov 3, 2024
  • .github Public
    explodinggradients/.github’s past year of commit activity
    0 1 0 0 Updated Oct 30, 2024
  • notes Public

    Research notes and extra resources for all the work at explodinggradients.com

    explodinggradients/notes’s past year of commit activity
    Jupyter Notebook 20 5 0 0 Updated Apr 23, 2024
  • LLaMA-Factory Public Forked from hiyouga/LLaMA-Factory

    Unify Efficient Fine-tuning of 100+ LLMs

    explodinggradients/LLaMA-Factory’s past year of commit activity
    Python 1 Apache-2.0 4,591 0 0 Updated Mar 3, 2024
  • Funtuner Public

    Supervised instruction finetuning for LLM with HF trainer and Deepspeed

    explodinggradients/Funtuner’s past year of commit activity
    Python 34 Apache-2.0 5 0 0 Updated Jul 6, 2023
  • nemesis Public

    Reward Model framework for LLM RLHF

    explodinggradients/nemesis’s past year of commit activity
    Python 58 Apache-2.0 3 4 1 Updated Jun 7, 2023

Sponsoring

  • @squidfunk

Most used topics

Loading…
GitHub Sponsor