PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16 • 104
view article Article Prefill and Decode for Concurrent Requests - Optimizing LLM Performance Apr 16 • 56
Llama 3.2 Collection Meta goes small with Llama3.2, both text only 1B and 3B, and the 11B Vision models. • 15 items • Updated Dec 17, 2024 • 13
LLaMA Beyond English: An Empirical Study on Language Capability Transfer Paper • 2401.01055 • Published Jan 2, 2024 • 55