view post Post 931 🚨🔥 New Release Alert! 🔥🚨Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥👉 Check it out: hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡)More details in our paper: https://arxiv.org/abs/2410.01524 📜#HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning 1 reply · 👀 6 6 🔥 4 4 + Reply
steiner-preview Collection Reasoning models trained on synthetic data using reinforcement learning. • 3 items • Updated Oct 20, 2024 • 32
Running on Zero 150 150 Chat With Janus 1.3B 🌍 A unified multimodal understanding and generation model.
Running 156 156 Whisper Large V3 Turbo WebGPU 🚀 ML-powered speech recognition directly in your browser