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: #miaospeed
@ffq_la · Post #191 · 06/13/2023, 05:29 AM
#miaospeed#release MiaoSpeed v4.3.4 ✅更新Clash内核 Clash v1.16.0 ✅更新Clash.Meta内核 Clash.Meta v1.14.5 ✅修复VLESS、Hysteria ✅新增Tuic支持（貌似主端不支持先加进去了） 地址：https://github.com/moshaoli688/miaospeed/releases/tag/v4.3.4
Hashtags
@ffq_la · Post #163 · 03/09/2023, 09:04 AM
#miaospeed#预告 ✅PING和UDP的DNS预解析 ✅Miaoko传入STUN或pingAddress无法解析自动切换Miaospeed内置地址 该条消息随时可能更新
Hashtags
@jngchannel · Post #1893 · 03/04/2023, 07:07 AM
#MiaoSpeed-4.3.1 #独家更新_自我编译 ✅更新Clash内核 ✅修复IP查询 ✅修复UDP检测 ✅修改默认测速链接轮询 ✅优化测试，缩减检测时间 😭预计在x时x分推送 😀看我摆烂否
Hashtags
@ffq_la · Post #153 · 03/07/2023, 04:05 PM
#miaospeed#dev版 #4.3.2 ✅同步Miaospeed 4.3.1 ✅更新Clash内核 Clash v1.13.0 ✅修复STUN无法传参问题 ✅ipv6 stack 读取问题 ✅默认 ipv6 检测脚本换为更激进的[2606:4700:4700:.1111] ✅增加一个新的动态测速文件方式， DYNAMIC:ALL (欢迎提交测速文件地址) ❌尝试更新Clash.META内核失败，保留原本的版本
Hashtags
@ffq_la · Post #165 · 03/13/2023, 08:32 AM
#miaospeed#release#v4.3.3 ✅同步Miaospeed 4.3.1 ✅更新Clash内核 Clash v1.13.0 ✅修复STUN无法传参问题 ✅PING和UDP的DNS预解析 ✅ipv6 stack 读取问题 ✅默认 ipv6 检测脚本换为更激进的[2606:4700:4700:.1111] ✅增加一个新的动态测速文件方式， DYNAMIC:ALL (欢迎提交测速文件地址) ✅Miaoko传入STUN或pingAddress无法解析自动切换Miaospeed内置地址 地址：https://github.com/moshaoli688/miaospeed/releases/tag/v4.3.3
Hashtags