SwiftKV Models Collection SwiftKV reduces prefill compute by up to 50% by combining model rewiring and knowledge-preserving self-distillation. • 3 items • Updated 29 days ago • 3
view article Article Fine-tune ModernBERT for text classification using synthetic data By davidberenstein1957 • 3 days ago • 16
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey Paper • 2412.18619 • Published 18 days ago • 43
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search Paper • 2412.18319 • Published 10 days ago • 31
view article Article Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth By mlabonne • Jul 29, 2024 • 260
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design Paper • 2412.14590 • Published 15 days ago • 13
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator Paper • 2412.12094 • Published 17 days ago • 10
Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents Paper • 2412.13194 • Published 16 days ago • 12
Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture Paper • 2412.11834 • Published 17 days ago • 6
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published 16 days ago • 116
ModernBERT Collection Bringing BERT into modernity via both architecture changes and scaling • 3 items • Updated 14 days ago • 111
OmniEval Collection An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain • 7 items • Updated about 19 hours ago • 2