Post

Hugging Face x Unsloth

Unsloth AI๐Ÿฆฅ just hit 1 million monthly downloads on Hugging Face today!๐Ÿฅณ We make LLM finetuning 2x faster and use 70% less memory with no accuracy degradation!

We have free finetuning notebooks on our Github page for Llama-3, Mistral and Gemma! Inference is also 2x faster!

Free notebook to finetune Llama-3: https://colab.research.google.com/drive/1XamvWYinY6FOSX9GLvnqSjjsNflxdhNc?usp=sharing

Our Hugging Face page: <huggingface.co/unsloth>

Join our Discord for AI banter, Q&A: https://discord.com/invite/u54VK8m8tk

And star us on Github! https://github.com/unslothai/unsloth

 Unsloth of Huggingface

Translate to Korean

๐Ÿฆฅ Unsloth AI ์˜ค๋Š˜ Hugging Face ์—์„œ ์›”๊ฐ„ ๋‹ค์šด๋กœ๋“œ 100๋งŒ ๊ฑด์„ ๋ŒํŒŒํ–ˆ์Šต๋‹ˆ๋‹ค! ๐Ÿฅณ LLM ๋ฏธ์„ธ ์กฐ์ • ์†๋„๋ฅผ 2๋ฐฐ ๋†’์ด๊ณ  ์ •ํ™•๋„ ์ €ํ•˜ ์—†์ด ๋ฉ”๋ชจ๋ฆฌ๋ฅผ 70% ์ ๊ฒŒ ์‚ฌ์šฉํ•ฉ๋‹ˆ๋‹ค!

Github ํŽ˜์ด์ง€์—์„œ Llama-3, Mistral, Gemma์— ๋Œ€ํ•œ ๋ฌด๋ฃŒ ๋ฏธ์„ธ ์กฐ์ • ๋…ธํŠธ๋ถ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค! ์ถ”๋ก ๋„ 2๋ฐฐ ๋” ๋นจ๋ผ์กŒ์Šต๋‹ˆ๋‹ค!

Llama-3 ๋ฏธ์„ธ ์กฐ์ •์„์œ„ํ•œ ๋ฌด๋ฃŒ ๋…ธํŠธ๋ถ : https://colab.research.google.com/drive/1XamvWYinY6FOSX9GLvnqSjjsNflxdhNc?usp=sharing

ํ—ˆ๊น… ํŽ˜์ด์Šค ํŽ˜์ด์ง€: <huggingface.co/unsloth>

AI ๋†๋‹ด, Q&A๋ฅผ ์œ„ํ•œ Discord์— ์ฐธ์—ฌํ•˜์„ธ์š”: https://discord.com/invite/u54VK8m8tk

๊ทธ๋ฆฌ๊ณ  Github์—์„œ ๋ณ„์„ ๋ณด๋‚ด์ฃผ์„ธ์š”! https://github.com/unslothai/unsloth

This post is licensed under CC BY 4.0 by the author.