view post Post 1473 Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2. up to 6.3× faster for image generation and editing.Try it here: PrunaAI/Pruna-Qwen-Image-2.1 See translation 🔥 5 5 + Reply
Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms Paper • 2609.23658 • Published 7 days ago • 27
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Paper • 2609.29845 • Published 3 days ago • 62
prism-ml/Ternary-Bonsai-2-27B-gguf Text Generation • 27B • Updated about 16 hours ago • 3.25M • 2.11k
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published 6 days ago • 206
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 10 days ago • 181
view post Post 4919 📣 HF Viewer now has a HF space! 🤗 embedl/hfviewerVisualize any model directly on Hugging Face - now 4,727 graphs!If you like it, feel free to give the space a heart to help it grow! ❤️And you can reply with any feedback or feature requests here! See translation 🔥 16 16 🧠 1 1 👍 1 1 + Reply
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them? Paper • 2609.10226 • Published 18 days ago • 19