ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models Paper • 2508.18773 • Published 13 days ago • 14
Running 61 61 LFM2 WebGPU – In-browser tool calling 🛠 In-browser tool calling, powered by Transformers.js
view post Post 5467 LiquidAI open-sources a new generation of edge LLMs! 🥳Based on a new hybrid architecture, these 350M, 700M, and 1.2B models are both fast and performant, ideal for on-device deployment.I recommend fine-tuning them to power your next edge application. We already provide Colab notebooks to guide you. More to come soon!📝 Blog post: https://www.liquid.ai/blog/liquid-foundation-models-v2-our-second-series-of-generative-ai-models🤗 Models: LiquidAI/lfm2-686d721927015b2ad73eaa38 See translation 1 reply · 🔥 15 15 👍 3 3 + Reply
💧 LFM2 Collection LFM2 is a new generation of hybrid models, designed for on-device deployment. • 15 items • Updated 3 days ago • 94