https://huggingface.co/blog/peft
LLM
PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware
by OBG posted Apr 15, 2024
Who's OBG
Articles
- GDB Dashboard
- AI-hub 공공데이터를 활용하여 한국어-영어 번역 LLM 만들기
- OS in 1,000 Lines
- 얼렁뚱땅 LLM을 만들어보자
- Comparing Replit and Cursor for AI-Powered Coding
- Synology: Top Best Apps For Docker
- ASCII 3D 렌더러 만들기
- Anthropic, LLM의 내부를 이해하는데 있어 상당한 진전을 보임
- llama3 implemented from scratch
- HuggingFace 공동창업자가 추천하는 AI 분야 입문 서적
- [VESSL AI] 뉴욕주민의 프로젝트플루토 — LLM, LLMOps를 활용한 금융 미디어의 혁신
- PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Har...
- The difference between quantization methods for the same bits
- Mixture of Experts - Part 2
- ChatGPT의 강력한 경쟁 언어모델 등장!, Mixtral 8x7B
- Real-Time Stock News Sentiment Prediction with Python
- Getting Started with Sentiment Analysis using Python
- How LLMs Work ? Explained in 9 Steps — Transformer Architecture
- 만능 프롬프트
- A Beginner's Guide to Prompt Engineering with GitHub Copilot