#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
🪙 32,137 #BTC ($2.18 billion) went from the wallet of the #Mt․Gox exchange that collapsed in 2014 to an unknown address — the market reacted with a drop, suggesting that payments to the exchange's creditors could begin at any moment.
⚫️The Black Swan arrived unexpectedly... wait for new comments, despite the unpleasant surprise, the situation may become an opportunity to enter the market and make money on non-negative growth.
😙 The reasons for the fall of the # bitcoin exchange rate below $61,000
The unemployment rate was 4.3%, which is higher than expected, indicating a possible recession
The Bank of Japan raised the interest rate for the first time in 17 years, which led to an outflow of investments from risky assets
Increased geopolitical tensions (fear of a major world war)
😏Continued distribution of #BTC from #Mt.Gox and #Genesis