#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
A whale is facing potential liquidations of 488.45 $WBTC($26.47M) on #Compound, with a health rate as low as 1.07 and a liquidation price of $50,429.
This whale was liquidated 3 times during the 2022 price crash, with a total of 74,426 $cWBTC($32.82M) being liquidated.
Address:
0xceef57f6c40a7cb2392eaad101ee0440aa43ba42
Lookonchain | ꘜ
Whales are accumulating $LINK.
Whale 0x3c9E withdrew 510,000 $LINK($11.13M) from #Binance over the past 2 days and deposited it into #Compound.
0x42A1 spent $1.34M to buy 59,560 $LINK 4 hours ago.
0x848a spent $1M to buy 44,846 $LINK 5 hours ago.
https://intel.arkm.com/explorer/address/0x3c9Ea5C4Fec2A77E23Dd82539f4414266Fe8f757
https://intel.arkm.com/explorer/address/0x42A1Cf900c55EC4eBC885eB870A8E1d2E2FA1727
https://intel.arkm.com/explorer/address/0x848aA08a594a14664685e7bbB3a00E38Faba4F2f