#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
Curated Crypto | ꘜ
🤑WTF: ETH options open interest just hit a 1.5-year high!
Degens are loading up on longs, while whales are stacking ETH at all-time record pace!
But hedge funds are going mega short - CME ETH futures short positioning just keeps smashing new records!
Green But Red in real life!
#WTF
The suspect attempted to escape an interrogation room by breaking through the wall while no one was watching—only to be caught shortly after.
@Viral_Today / #wtf
Imagine a coffee table that moves around the house by itself—well, you don’t have to anymore because it’s real. It’s just as fascinating as it is creepy.
@Viral_Today / #wtf