#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
https://github.com/aio-libs/aiohttp-mako
#mako template renderer for #aiohttp.web based on aiohttp_jinja2. Library has almost same api and support python 3.5 (PEP492) syntax. It is used in aiohttp_debugtoolbar.
#Mako is a #template library written in Python. It provides a familiar, non-XML syntax which compiles into Python modules for maximum performance. Mako's syntax and #API borrows from the best ideas of many others, including #Django and #Jinja2 templates, #Cheetah, #Myghty, and #Genshi. Conceptually, Mako is an embedded Python (i.e. Python Server Page) language, which refines the familiar ideas of componentized layout and inheritance to produce one of the most straightforward and flexible models available, while also maintaining close ties to Python calling and scoping semantics.
http://www.makotemplates.org/