Pull requests help you collaborate on code with other people. As pull requests are created, they’ll appear here in a searchable and filterable list. To get started, you should create a pull request.

1.2 OCR Extract Text from PDF Supported by AI models ... 2 Smart AI Chatbot, Support All AI Models Integrated with ChatGPT-4o-mini, DeepSeek V3, DeepSeek R1, LLama 3.3 70B, Claude 3 Haiku, and Gamma3, ...

Meta’s upcoming Llama 4, with a release date likely later this year, is widely expected to feature reasoning capabilities and allow for AI agents to use a web browser and other tools.

The company also shared some examples of how Llama is being used by companies all over the world to improve their products and services. Meta says Spotify, the popular music streaming platform with ...

Seven llamas perished in a barn fire at Louisville Llama Farm, owned by Caroline Willette and Dale Hill. The cause of the fire is still under investigation, but it may have been caused by faulty ...

In a brief message Tuesday morning on Threads, Meta CEO Mark Zuckerberg said the company’s “open” AI model family, Llama, hit 1 billion downloads. That’s up from 650 million downloads as ...

Llama 3.2 Vision is Meta's latest open-source vision-language model that can process both text and images. It is a collection of instruction-tuned image reasoning generative models in 11B and 90B ...

Our open source AI model, Llama, has been downloaded more than one billion times. We believe open sourcing AI models is essential to ensuring people everywhere have access to the benefits of AI, and ...

For example, in full-page document OCR tasks, SmolDocling achieved significantly better accuracy metrics, such as a notably lower edit distance (0.48) and higher F1-score (0.80), compared to models ...

Optical Character Recognition (OCR) is a powerful technology that converts images of text into machine-readable content. With the growing need for automation in data extraction, OCR tools have become ...