cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental Viewer โข Updated Aug 15, 2024 โข 29.2k โข 47 โข 21
PaddlePaddle/PaddleOCR-VL-1.5 Image-Text-to-Text โข 1.0B โข Updated about 16 hours ago โข 26.7k โข 657
๐ฏ Liquid Nanos Collection Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices โข 34 items โข Updated 15 days ago โข 122
view post Post 3821 ๐ค Who would win ?- a fully subsidized ai lab OR - 3 random students named kurakurai ? demo : Tonic/fr-on-deviceif you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding . See translation 4 replies ยท ๐ฅ 11 11 + Reply
view post Post 959 granite-4.0-350m, rwkv7-g1d-0.4b and LFM2-350M are currently the best sub 0.5b models currently for fewshot, simple language tasksno one is saying this:if you need the absolute speed + small size + quality, granite 350m is the current king See translation 3 replies ยท ๐ 4 4 + Reply
view post Post 10483 New family of 1B models just dropped!> LiquidAI/LFM2.5-1.2B-Base: 10T โ 28T tokens> LiquidAI/LFM2.5-1.2B-Instruct: new large-scale multi-stage RL> LiquidAI/LFM2.5-1.2B-JP: our most polite model> LiquidAI/LFM2.5-VL-1.6B: multi-image multilingual> LiquidAI/LFM2.5-Audio-1.5B: 8x times faster, no quality lossSuper proud of this release ๐ค See translation 3 replies ยท ๐ 18 18 ๐ 1 1 + Reply