TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub Trends

TGINSIGHT SIMILAR POSTS

Find similar content

Source channel @githubtrending · Post #15432 · Jan 23

#jupyter_notebook#chinese_llm#chinese_nlp#finetune#generative_ai#instruct_gpt#instruction_set#llama#llm#lora#open_models#open_source#open_source_models#qlora AirLLM is a tool that lets you run very large AI models on computers with limited memory by using a smart layer-by-layer loading technique instead of traditional compression methods. You can run a 70-billion-parameter model on just 4GB of GPU memory, or even a 405-billion-parameter model on 8GB, without losing model quality. The benefit is that you can use powerful AI models on affordable hardware without expensive upgrades, and the tool also offers optional compression features that can speed up performance by up to 3 times while maintaining accuracy. https://github.com/lyogavin/airllm

Results

1 similar post found

Search: #bandgap

当前筛选 #bandgap清除筛选

Опубликована новая статья 🟣 2024 🟣 V. 11 🟣 Issue 2 🟣 Art. 202411207 🟣 Letter 🟣 📜 Features of electronic states in the vicinity of band gap and atomic structure of Ta- and Nb-doped Li7La3Zr2O12 👩‍🎓👨‍🎓 M. I. Vlasov (http://orcid.org/0000-0002-7814-7489), E.A. Surzhikov (http://orcid.org/0009-0005-3466-6374), A.Yu. Germov (http://orcid.org/0000-0001-6091-1250), E.A. Il'ina (http://orcid.org/0000-0003-1759-5234), I.A. Weinstein (http://orcid.org/0000-0002-5573-7128) 🏛 Institute of High Temperature Electrochemistry of the Ural Branch of the Russian Academy of Sciences, https://ihte.ru/?page_id=3106 🏛 Ural Federal University, https://urfu.ru/en 🏛 M.N. Mikheev Institute of Metal Physics of the Ural Branch of the Russian Academy of Sciences, https://www.imp.uran.ru/?q=en 🏛 Institute of Metallurgy of the Ural Branch of the Russian Academy of Sciences, http://www.imet-uran.ru 📚#Li7La3Zr2O12#Ta#Nb#doping#bandgap#oxygen#vacancies 🔗https://doi.org/10.15826/chimtech.2024.11.2.07 https://journals.urfu.ru/index.php/chimtech/article/view/7692