
Cohere has unveiled Tiny Aya, a new series of multilingual models tailored for edge computing applications. These models are designed to improve performance in multilingual tasks, making them suitable for diverse applications. The launch includes a blog detailing the models, a paper, and resources available on Hugging Face and Google Colab for developers. This development signifies a step forward in making multilingual AI more accessible and efficient for edge use cases.
Read originalThe latest version b8991 of llama.cpp has been released, featuring updates for various operating systems.
The latest update to llama-mmap improves compatibility with various platforms and model sizes. Key enhancements include support for 32-bit wasm and updates to gguf.cpp style.
