Unsloth 4-bit Dynamic Quants Collection Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 7 items • Updated about 6 hours ago • 20
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs Paper • 2410.05295 • Published Oct 3 • 12
HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models Paper • 2409.16191 • Published Sep 24 • 41
Training Language Models to Self-Correct via Reinforcement Learning Paper • 2409.12917 • Published Sep 19 • 135
Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment Paper • 2408.06266 • Published Aug 12 • 9
Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning Paper • 2407.15762 • Published Jul 22 • 9
Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies Paper • 2407.13623 • Published Jul 18 • 53
NeedleBench: Can LLMs Do Retrieval and Reasoning in 1 Million Context Window? Paper • 2407.11963 • Published Jul 16 • 43
Llama 3.1 Collection This collection hosts the transformers and original repos of the Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated 19 days ago • 636
Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis Paper • 2407.12173 • Published Jul 16 • 2
No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models Paper • 2407.02687 • Published Jul 2 • 22
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion Paper • 2407.01392 • Published Jul 1 • 39
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding Paper • 2406.19389 • Published Jun 27 • 52
WARP: On the Benefits of Weight Averaged Rewarded Policies Paper • 2406.16768 • Published Jun 24 • 22
DiffusionPDE: Generative PDE-Solving Under Partial Observation Paper • 2406.17763 • Published Jun 25 • 23
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale Paper • 2406.17557 • Published Jun 25 • 87