#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
🐂🐂🐂🐂🐂🐂
According to analysts, a BTC-ETF called #iShares Bitcoin Trust from #BlackRock has surpassed #GTC from Grayscale in terms of the number of coins at its core. Accordingly, it is now the largest #BTC spot exchange-traded fund in the United States.
Bloomberg analyst Eric Balchunas confirmed the leadership of the #BlackRock iShares Bitcoin Trust (BUT) among spot BTC ETFs. Recall that this exchange-traded fund bypassed Grayscale's GTC based on the trading results for the last day.
As Eric noted, BlackRock is likely to occupy the top spot "for decades." The reason is a combination of low fees, serious liquidity and the excellent reputation of the iShares brand.
🐂🐂🐂🐂🐂🐂
🚀 Bitcoin ETFs See Strong Inflows as Market Interest Grows
US spot Bitcoin ETFs experienced significant net inflows exceeding $786 million last week, marking their most robust performance since February. According to NS3.AI, BlackRock's iShares Bitcoin Trust attracted approximately $612 million. Meanwhile, Morgan Stanley's newly launched MSBT fund garnered around $46 million within its initial three trading days.
#Bitcoin#ETFs#BlackRock#MorganStanley#CryptoInvestment#MarketInterest#MSBT#iShares#Inflow#BTC