view post Post 923 šØš„ New Release Alert! š„šØIntroducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! š»š„š Check it out: hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! š”)More details in our paper: https://arxiv.org/abs/2410.01524 š#HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning 1 reply Ā· š 5 5 š„ 4 4 + Reply
steiner-preview Collection Reasoning models trained on synthetic data using reinforcement learning. ā¢ 3 items ā¢ Updated Oct 20, 2024 ā¢ 27
Running on Zero 87 š Chat With Janus 1.3B A unified multimodal understanding and generation model.
Running 140 š Whisper Large V3 Turbo WebGPU ML-powered speech recognition directly in your browser
openai/whisper-large-v3-turbo Automatic Speech Recognition ā¢ Updated Oct 4, 2024 ā¢ 2.02M ā¢ ā¢ 1.72k