https://github.com/seungjaelim/k-hyunmoogpt

[K-Data Science Hackaton 3rd Award] Development and use of Korean large-scale generative language models
https://github.com/seungjaelim/k-hyunmoogpt

chromadb fine-tuning gradio koalpaca llm llm-inference rag sbert

Last synced: about 2 months ago
JSON representation

[K-Data Science Hackaton 3rd Award] Development and use of Korean large-scale generative language models

• Host: GitHub
• URL: https://github.com/seungjaelim/k-hyunmoogpt
• Owner: SeungjaeLim
• License: mit
• Created: 2023-12-01T05:41:23.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-12-01T05:54:14.000Z (almost 2 years ago)
• Last Synced: 2024-12-02T23:11:45.549Z (12 months ago)
• Topics: chromadb, fine-tuning, gradio, koalpaca, llm, llm-inference, rag, sbert
• Language: Python
• Homepage:
• Size: 21 MB
• Stars: 2
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# K-HyunmooGPT

## K-Data Science Hackaton 3rd Award

# Development and use of Korean large-scale generative language models

20231128~20231129 

---

![image](https://github.com/daily-kim/K-DS-Hackaton_History_LLM/assets/90249131/2887beb0-cc2b-445e-9c78-c8aa265168ee)

* LLM serving

  * Local server (1* RTX 6000)

  * Docker

  * HuggingFace pipeline

* LLM Finetuning

  * Original model from [KoAlpaca-Polyglot-5.8B](https://huggingface.co/beomi/KoAlpaca-Polyglot-5.8B)

  * Finetuned using Peft+LoRA

* [RAG](https://github.com/venzino-han/history_rag)

  * ChromaDB

  * FastAPI

  * Docker

* Gradio

  * Original code from [Baize](https://huggingface.co/spaces/project-baize/chat-with-baize)

* Prompoting

  

...