wangclnlp/DeepSpeed-Chat-Extension

This repo contains some extensions of deepspeed-chat for fine-tuning LLMs (SFT+RLHF).

26
/ 100
Experimental

This project helps machine learning engineers and researchers improve the quality and safety of large language models (LLMs) by fine-tuning them with various advanced techniques. It takes your existing LLM and curated datasets (text for supervised fine-tuning, preference data for reward modeling, or conversational turns for multi-turn dialogues) and outputs a more refined, aligned, and performant LLM ready for deployment. This tool is for AI practitioners focused on building highly effective conversational AI.

No commits in the last 6 months.

Use this if you need to fine-tune large language models like LLaMA or Baichuan with state-of-the-art alignment techniques, including Direct Preference Optimization (DPO) or Reinforcement Learning from Human Feedback (RLHF), to enhance their performance on specific tasks or user preferences.

Not ideal if you are a business user looking for a no-code solution, or if you only need basic LLM inference without advanced fine-tuning capabilities.

LLM fine-tuning conversational AI machine learning research AI model alignment natural language processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

21

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Jul 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/wangclnlp/DeepSpeed-Chat-Extension"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.