awesome-llama: https://github.com/michaelnny/QLoRA-LLM

4bit-quantize custom-model fine-tuning llama llm qlora

Score: 2.3978952727983707

Last synced: about 24 hours ago
JSON representation

Repository metadata:

A simple custom QLoRA implementation for fine-tuning a language model (LLM) with basic tools such as PyTorch and Bitsandbytes, completely decoupled from Hugging Face.

• Host: GitHub
• URL: https://github.com/michaelnny/QLoRA-LLM
• Owner: michaelnny
• License: mit
• Created: 2023-12-13T14:08:35.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-01-29T07:50:59.000Z (about 2 years ago)
• Last Synced: 2026-02-22T12:22:44.680Z (about 1 month ago)
• Topics: 4bit-quantize, custom-model, fine-tuning, llama, llm, qlora
• Language: Python
• Homepage:
• Size: 26 MB
• Stars: 10
• Watchers: 0
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

---

Owner metadata:

• Name: Michael Hu
• Login: michaelnny
• Email:
• Kind: user
• Description: Passionate about Deep Learning and Reinforcement Learning.
• Website:
• Location: Shanghai
• Twitter:
• Company:
• Icon url: https://avatars.githubusercontent.com/u/56952187?v=4
• Repositories: 2
• Last Synced at: 2023-03-09T04:50:53.237Z
• Profile URL: https://github.com/michaelnny

---

GitHub Events

Total

• Watch event: 7
• Total: 7

Last Year

• Total: 0

---

Committers metadata

Last synced: 19 days ago

Name	Email	Commits
Michael Hu	m****y@g****m	12

---

Issue and Pull Request metadata

Last synced: 25 days ago

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/michaelnny/QLoRA-LLM

---

---

---

Dependencies