awesome-llama: https://github.com/jackaduma/Vicuna-LoRA-RLHF-PyTorch

chatgpt finetune gpt llama llm lora peft ppo pytorch reward-models rlhf vicuna vicuna-7b

Score: 5.4680601411351315

Last synced: 1 minute ago
JSON representation

Repository metadata:

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

• Host: GitHub
• URL: https://github.com/jackaduma/Vicuna-LoRA-RLHF-PyTorch
• Owner: jackaduma
• License: mit
• Created: 2023-04-22T05:09:55.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2024-05-20T13:10:39.000Z (over 1 year ago)
• Last Synced: 2026-02-06T07:56:10.320Z (3 days ago)
• Topics: chatgpt, finetune, gpt, llama, llm, lora, peft, ppo, pytorch, reward-models, rlhf, vicuna, vicuna-7b
• Language: Python
• Homepage:
• Size: 18.7 MB
• Stars: 221
• Watchers: 6
• Forks: 18
• Open Issues: 16
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

---

Owner metadata:

• Name: MK
• Login: jackaduma
• Email:
• Kind: user
• Description:
• Website: https://jackaduma.github.io/
• Location: Nanjing, China
• Twitter: jackaduma
• Company: Chocolate Factory
• Icon url: https://avatars.githubusercontent.com/u/1276942?u=1175c1d8dfc3009b5ff36eba21f09a1da058e375&v=4
• Repositories: 36
• Last Synced at: 2023-08-02T19:59:15.657Z
• Profile URL: https://github.com/jackaduma

---

GitHub Events

Total

• Fork event: 1
• Watch event: 14
• Total: 15

Last Year

• Fork event: 1
• Watch event: 9
• Total: 10

---

Committers metadata

Last synced: 1 day ago

Name	Email	Commits
Kun Ma	j****a@g****m	21

---

Issue and Pull Request metadata

Last synced: 5 months ago

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/jackaduma/Vicuna-LoRA-RLHF-PyTorch

---

---