CroissantLLM weights in Machine Learning Compilation (MLC) format, with q4f32 quantization.
Learn more about Machine Learning Compilation and how to use these weights here.
Inference API (serverless) is not available, repository is disabled.
CroissantLLM weights in Machine Learning Compilation (MLC) format, with q4f32 quantization.
Learn more about Machine Learning Compilation and how to use these weights here.