# jackaduma/Vicuna-LoRA-RLHF-PyTorch

<https://repo.masters-masters.com/en/repos/jackaduma/Vicuna-LoRA-RLHF-PyTorch>

[Home](https://repo.masters-masters.com/en) › [jackaduma](https://repo.masters-masters.com/en/owners/jackaduma) › [Vicuna-LoRA-RLHF-PyTorch](https://repo.masters-masters.com/en/repos/jackaduma/Vicuna-LoRA-RLHF-PyTorch)

jackaduma/Vicuna-LoRA-RLHF-PyTorch has 219 stars on GitHub. Its RepoMasters card: Prototype tier. A full pipeline to finetune Vicuna LLM with LoRA and RLHF on…

| Field | Value |
| --- | --- |
| Owner | [jackaduma](https://repo.masters-masters.com/en/owners/jackaduma) |
| Stars | 219 |
| Forks | 18 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | MIT |
| Created | 2023 |
| Topics | chatgpt, finetune, gpt, llama, llm, lora, peft, ppo, pytorch, reward-models |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [jackaduma/Vicuna-LoRA-RLHF-PyTorch](https://github.com/jackaduma/Vicuna-LoRA-RLHF-PyTorch) |

## Repository

A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Vicuna architecture. Basically ChatGPT but with Vicuna

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## More repos by jackaduma

- [jackaduma/awesome\_LLMs\_interview\_notes · ★ 1,320 · Beta](https://repo.masters-masters.com/en/repos/jackaduma/awesome_LLMs_interview_notes)
- [jackaduma/CycleGAN-VC2 · ★ 572 · Python · Alpha](https://repo.masters-masters.com/en/repos/jackaduma/CycleGAN-VC2)
- [jackaduma/SecBERT · ★ 214 · Python · Prototype](https://repo.masters-masters.com/en/repos/jackaduma/SecBERT)
- [jackaduma/Recurrent-LLM · ★ 207 · Python · Prototype](https://repo.masters-masters.com/en/repos/jackaduma/Recurrent-LLM)
- [jackaduma/CycleGAN-VC3 · ★ 157 · Python · Prototype](https://repo.masters-masters.com/en/repos/jackaduma/CycleGAN-VC3)
- [jackaduma/ChatGLM-LoRA-RLHF-PyTorch · ★ 138 · Python · Prototype](https://repo.masters-masters.com/en/repos/jackaduma/ChatGLM-LoRA-RLHF-PyTorch)

## Nearby in Python

- [Taiquan-Zhou/RunTheRepo · ★ 219 · Python · Prototype](https://repo.masters-masters.com/en/repos/Taiquan-Zhou/RunTheRepo)
- [InferMatrixLab/vllm-rlt · ★ 219 · Python · Prototype](https://repo.masters-masters.com/en/repos/InferMatrixLab/vllm-rlt)
- [duyunzhoudyz/gongwen-skills · ★ 219 · Python · Prototype](https://repo.masters-masters.com/en/repos/duyunzhoudyz/gongwen-skills)
- [bwaldvogel/neighbourhood · ★ 219 · Python · Prototype](https://repo.masters-masters.com/en/repos/bwaldvogel/neighbourhood)
- [hpfeeds/hpfeeds · ★ 219 · Python · Prototype](https://repo.masters-masters.com/en/repos/hpfeeds/hpfeeds)
- [5quinque/Soundcloud-Downloader · ★ 219 · Python · Prototype](https://repo.masters-masters.com/en/repos/5quinque/Soundcloud-Downloader)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.