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: #librecellular

当前筛选 #librecellular清除筛选
Libreware

@libreware · Post #957 · 06/22/2021, 01:28 PM

— LibreCellular 21.04 documentation –https://librecellular.org/ The LibreCellular project aims to make it easier to create #4G cellular #networks with open source software and low cost software-defined radio (#SDR) hardware. Seeking to achieve this via validated hardware and software configurations that are subjected to rigorous testing, together with additional tooling and #documentation for repeatable deployment. LibreCellular will build on the work of numerous existing open source software and hardware projects, related to both the #cellular platform itself and associated test #infrastructure. Where necessary additional components will be developed, with any software source code and #hardware designs published under #opensource licences. The focus is very much on integration, testing, packaging and documentation, reusing and building upon existing solutions.. #LibreCellular#CellulaireLibre