awesome-llama: https://github.com/l294265421/alpaca-rlhf

alpaca chatgpt language-model large-language-models llama llm reinforcement-learning rlhf

Score: 5.529429087511423

Last synced: about 5 hours ago
JSON representation

Repository metadata:

Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat

• Host: GitHub
• URL: https://github.com/l294265421/alpaca-rlhf
• Owner: l294265421
• License: mit
• Created: 2023-04-12T08:19:46.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2023-06-05T00:47:02.000Z (about 3 years ago)
• Last Synced: 2026-06-02T09:03:22.011Z (14 days ago)
• Topics: alpaca, chatgpt, language-model, large-language-models, llama, llm, reinforcement-learning, rlhf
• Language: Python
• Homepage: https://88aeeb3aef5040507e.gradio.live/
• Size: 97.9 MB
• Stars: 117
• Watchers: 2
• Forks: 15
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

---

Owner metadata:

• Name: 慢半拍
• Login: l294265421
• Email:
• Kind: user
• Description: 练拳不练功，到老一场空
• Website: https://scholar.google.com/citations?user=DDe-NB4AAAAJ&hl=zh-CN
• Location: 深圳
• Twitter:
• Company: Tencent
• Icon url: https://avatars.githubusercontent.com/u/9948265?u=c8d5e336a78ab7fb32a8ab9dc93f7eea19902ee9&v=4
• Repositories: 9
• Last Synced at: 2023-03-03T02:06:17.004Z
• Profile URL: https://github.com/l294265421

---

GitHub Events

Total

• Fork event: 2
• Watch event: 11
• Total: 13

Last Year

• Fork event: 1
• Watch event: 1
• Total: 2

---

Committers metadata

Last synced: 2 days ago

Name	Email	Commits
yuncongli	y****i@t****m	82
慢半拍	2****1@q****m	1

---

Issue and Pull Request metadata

Last synced: 10 months ago

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/l294265421/alpaca-rlhf

---

---

---

Dependencies