Beomi / Gemma-EasyLMLinks
Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)
โ48Updated last year
Alternatives and similar repositories for Gemma-EasyLM
Users that are interested in Gemma-EasyLM are comparing it to the libraries listed below
Sorting:
- Official repository for KoMT-Bench built by LG AI Researchโ69Updated last year
- ๐ค ์ต์ํ์ ์ธํ ์ผ๋ก LM์ ํ์ตํ๊ธฐ ์ํ ์ํ์ฝ๋โ58Updated 2 years ago
- [KO-Platy๐ฅฎ] Korean-Open-platypus๋ฅผ ํ์ฉํ์ฌ llama-2-ko๋ฅผ fine-tuningํ KO-platypus modelโ75Updated last month
- bpe based korean t5 model for text-to-text unified frameworkโ63Updated last year
- Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adcโ80Updated last year
- Benchmark in Korean Contextโ136Updated 2 years ago
- โ108Updated 2 months ago
- ๊ตฌ๊ธ์์ ๋ฐํํ Chain-of-Thought Reasoning without Prompting์ ์ฝ๋๋ก ๊ตฌํํ ๋ ํฌ์ ๋๋ค.โ67Updated last year
- StrategyQA ๋ฐ์ดํฐ ์ธํธ ๋ฒ์ญโ22Updated last year
- โ107Updated 2 years ago
- โ36Updated 2 years ago
- [Google Meet] MLLM Arxiv Casual Talkโ52Updated 2 years ago
- huggingface์ ์๋ ํ๊ตญ์ด ๋ฐ์ดํฐ ์ธํธโ30Updated last year
- IA3๋ฐฉ์์ผ๋ก KoAlpaca๋ฅผ fine tuningํ ํ๊ตญ์ด LLM๋ชจ๋ธโ69Updated 2 years ago
- ์์ฒด ๊ตฌ์ถํ ํ๊ตญ์ด ํ๊ฐ ๋ฐ ์ดํฐ์ ์ ์ด์ฉํ ํ๊ตญ์ด ๋ชจ๋ธ ํ๊ฐโ31Updated last year
- For the rlhf learning environment of Koreansโ25Updated 2 years ago
- Reward Model์ ์ด์ฉํ์ฌ ์ธ์ด๋ชจ๋ธ์ ๋ต๋ณ์ ํ๊ฐํ๊ธฐโ29Updated last year
- ํ๊ตญ์ด ์ฌ๋ฆฌ ์๋ด ๋ฐ์ดํฐ์ โ78Updated 2 years ago
- ํ๊ตญ์ด T5 ๋ชจ๋ธโ54Updated 3 years ago
- The most modern LLM evaluation toolkitโ70Updated 2 weeks ago
- CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Koreanโ47Updated 9 months ago
- OpenOrca-KO dataset์ ํ์ฉํ์ฌ llama2๋ฅผ fine-tuningํ Korean-OpenOrcaโ19Updated last year
- โ68Updated last year
- Liner LLM Meetup archiveโ71Updated last year
- ํ๊ตญ์ด ์๋ฃ ๋ถ์ผ ํนํ ์ฑ๋ด ํ๋ก์ ํธโ32Updated last year
- Korean Math Word Problemsโ59Updated 3 years ago
- LINER PDF Chat Tutorial with ChatGPT & Pineconeโ47Updated 2 years ago
- โ32Updated 2 years ago
- โ19Updated last year
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the modelโs latent reasoning capabilโฆโ113Updated 3 months ago