view article Article KV Caching Explained: Optimizing Transformer Inference Efficiency Jan 30, 2025 • 233
view article Article Qwen-Image-i2L: Training Strategies for Image-to-LoRA Generation Dec 16, 2025 • 54
Qwen3-VL Collection Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats. • 56 items • Updated about 21 hours ago • 26
view article Article LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR Oct 23, 2025 • 73
Qualcomm NPU Collection Latest SOTA models supported on Qualcomm NPU. • 34 items • Updated Jan 15 • 8
Recent models: last 100 repos, sorted by creation date Collection The last 100 repos I have created. Sorted by creation date descending, so the most recently created repos appear at the top. • 121 items • Updated Jan 31, 2024 • 571
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 142
SmolDocling datasets Collection Datasets used to train SmolDocling • 6 items • Updated Jul 31, 2025 • 31