#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
💾 Bola 512 GB hajmdagi 50 ta SSDni sindirib qo‘ydi
💸 Bir erkak narxlar oshib borayotganini ko‘rib, xotira qurilmalariga sarmoya kiritmoqchi bo‘lib, 512 GB li 50 taSamsung PM991a SSD sotib olgan — jami qiymati taxminan $4000 bo‘lgan.
😱 Ammo ularning barchasini 10 yoshli o‘g‘li o'ynab, bukib chiqqan.
😭 Bechora bola… "detdom"ga ketarmikan?
➡️#ssd | Birinchi IT-Blog
Про #ssd почему скорость бывает падает, и что важно знать всем
https://news.fidller.com/2023/03/17/pochemu-vash-novyy-ssd-rabotayet-medlenno/
#newsfidllercom#bighousecinema