The current, most capable model that runs on a single GPU.
2.9M Pulls 17 Tags Updated 4 days ago
🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.
4.4M Pulls 98 Tags Updated 14 months ago
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
1.6M Pulls 9 Tags Updated 4 months ago
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
716.6K Pulls 17 Tags Updated 4 months ago
A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
529.2K Pulls 4 Tags Updated 10 months ago
moondream2 is a small vision language model designed to run efficiently on edge devices.
161.4K Pulls 18 Tags Updated 10 months ago
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
111.8K Pulls 17 Tags Updated 15 months ago
A new small LLaVA model fine-tuned from Phi 3 Mini.
84K Pulls 4 Tags Updated 10 months ago
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
31.1K Pulls 5 Tags Updated 4 weeks ago