TGINSIGHT SIMILAR POSTS
Source channel @githubtrending · Post #15432 · Jan 23
#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
Search: #l1
@ethereumglobalnews · Post #1454 · 12/01/2025, 06:57 AM
🪙 Vitalik: “You can just build on #L1” as fees stay cheap in 2025. #ETH 😎 Vitalik 表示: 由於 2025 年以太坊交易費持續保持低位，「直接在 L1 上構建」依然可行。今年以來 L1 需求增速溫和、區塊空間壓力未現顯著擁堵。 #Ethereum#DeFi#以太坊#市場趨勢 ——— ⚡️ 若費用長期維持低檔，L1 與 Rollup 的功能分工可能再度被市場重估 #Scaling ✅Chat: @Web3NewsInsight 🦂 👇Tip👇讚 或點擊進行💎資源搜索👇
@ethereumglobalnews · Post #1618 · 12/26/2025, 04:57 AM
🪙 L1 Tokens 2025 Performance Castle Labs data shows most Layer 1 tokens ended 2025 in negative territory. Only BNB (+18.2%) and TRX (+9.8%) managed to stay in positive returns. • ETH：-15.3% • SOL：-35.9% • SUI / AVAX：跌幅均超 -67% • TON：全年回撤接近 -74% ⚡️ 結構性行情下L1 不再齊漲齊跌 #Ethereum#L1#CryptoMarkets #OnChain#BNB#以太坊 —————— 👇⭐️👇 🤣 🥲👇 資源搜索 🖲️👆
@deep_school · Post #83 · 09/20/2022, 02:35 PM
Сегодня вторник, а значит в эфире рубрика “повторяем теорию”🤓 Вспомним про регуляризацию сетей, а именно про три популярных метода: L1, L2 и Dropout (ведь был популярен когда-то, надо отдать дань старичку). Статья в телеграфе 👉Регуляризуем правильно! #регуляризация#L1#L2#dropout
Hashtags