liyorozuya (@liyorozuya) 's Twitter Profile
liyorozuya

@liyorozuya

DB&Storage | t.me/KakarottoL|孤岛变星球|偶像卡卡罗特|梦想是开心快乐 |Never good enough|时间你在慢点吧🥺

ID: 914039476455751681

calendar_today30-09-2017 08:09:27

305 Tweet

28 Takipçi

278 Takip Edilen

François Fleuret (@francoisfleuret) 's Twitter Profile Photo

My deep learning course UNIGE_en is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch. fleuret.org/dlc/ And my "Little Book of Deep Learning" is available as a phone-formatted pdf (400k downloads!) fleuret.org/lbdl/

My deep learning course <a href="/unige_en/">UNIGE_en</a> is available on-line. 1000+ slides, ~20h of screen-casts.  Full of examples in <a href="/PyTorch/">PyTorch</a>.

fleuret.org/dlc/

And my "Little Book of Deep Learning" is available as a phone-formatted pdf (400k downloads!)

fleuret.org/lbdl/
F.viK (@amd3xcb6) 's Twitter Profile Photo

提示一下各位,人瑞基因有非常明显的遗传趋势。 如果在医疗条件充分完善的情况下,一位 105 岁老人的孩子,且不说活到 150 岁吧,活到 105 岁是一个高概率事件。 大家最好想想自己有没有信心活到 2058 年 🤤

徹言 (@iamcheyan) 's Twitter Profile Photo

fudoki.iamcheyan.com 想背些日语作文,但没找到好用的复读机应用,自己做了一个。 可以自己导入文章,TTS语音播报,无限循环复读。 唉,用我老婆的话说,人菜瘾大。 语言没学得多好,轮子倒是造了不少。

TuringPost (@theturingpost) 's Twitter Profile Photo

KV cache compression techniques ▪️KV caching (basic) – stores previously computed Keys and Values in memory and calculates attention only for new tokens. ▪️ Quantization – represents KV cache with fewer bits. ▪️ Low-rank decomposition – compresses the KV cache into smaller

KV cache compression techniques

▪️KV caching (basic) – stores previously computed Keys and Values in memory and calculates attention only for new tokens.

▪️ Quantization – represents KV cache with fewer bits.

▪️ Low-rank decomposition – compresses the KV cache into smaller
liyorozuya (@liyorozuya) 's Twitter Profile Photo

突然发现初恋访问了我的LinkedIn 然后发现她去了美国 内心不悦 同样的时间我大部分在生病😒😒😒😒 我要带夏夏环游世界