Models & Labs
Hugging Face Introduces Falcon Perception Model
Hugging Face Blogmedium confidence
Why it matters
- →The introduction of Falcon Perception represents a significant step forward in the capabilities of perception systems, particularly in integrating language and visual data.
Hugging Face has launched Falcon Perception, a 0.6 billion-parameter early-fusion Transformer model that integrates image and text processing for open-vocabulary grounding and segmentation. It utilizes a hybrid attention mask and a structured token interface, achieving a Macro-F1 score of 68.0 on the SA-Co benchmark, outperforming previous models. Additionally, the release includes Falcon OCR, a 0.3 billion-parameter model that excels in OCR tasks, achieving high scores on relevant benchmarks. This development highlights advancements in perception systems and their applications in image processing.
Read originalMore from Hugging Face Blog
More in Models & Labs
Models & Labsmodels
Llama.cpp adds GLM-5.2 speculative decoding support
Llama.cpp's latest update introduces speculative decoding support for GLM-5.2, enhancing its capabilities with NextN/MTP features. This addition allows for more efficient tensor loading and context management, particularly benefiting models using the GLM_DSA architecture. The update also includes options for exporting models with or without the MTP feature, providing flexibility for developers. This release marks a step forward in optimizing model performance and adaptability, especially for those leveraging the GLM-5.2 framework.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10178 Release Adds Trace Logging
The b10178 release of llama.cpp enhances its server capabilities by adding trace logging for slot similarity checking, offering developers detailed insights into prompt cache slot selection processes. This update includes specifics on skip reasons and similarity calculations, which can aid in performance optimization. While no new model architectures are introduced, the release continues to support a wide array of platforms, such as macOS with KleidiAI, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13. This makes llama.cpp a more versatile tool for developers working on different systems, reinforcing its position as a comprehensive inference runtime.
