#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
📊 ETFs | Weekly Flows Snapshot
SOL ETFs were the only ones with net inflows among the top 3 this week.
#ETF#Flows#Markets
#BTC#ETH#SOL#Crypto
———
結構解讀關鍵👇🥇資源搜索🖲️👆
📉 本週三大主流 ETF 資金流向出現明顯分化:
• BTC ETF:持續淨流出,賣壓集中於大型發行商
• ETH ETF:連續多日負流量,短線情緒偏保守
• SOL ETF:唯一錄得淨流入,資金逆勢布局
📈 結構解讀:
• 資金正在 避開高擁擠交易(BTC / ETH)
• SOL 成為短線輪動與主題交易承接標的
• ETF 流向顯示:市場並非全面風險退出,而是 選擇性進場
⚡️ 觀察重點:
若 SOL ETF 流入延續,可能代表
👉 資金正在測試「非 BTC / ETH 主流替代敘事」
👇⭐️👇
🤣留言分享觀點
🥲👇