Rahul D Shetty
Rahul D Shetty
### Feature request It seems we now have support for loading models using 4bit quantization starting from bitsandbytes>=0.39.0 Link: [FP4 Quantization](https://huggingface.co/docs/transformers/main_classes/quantization#fp4-quantization) ### Motivation Running really large language models on smaller...
There are early discussions of implementing WebGPU support in llama.cpp/ggml. Look into contributing and bringing the support in llm.js. - https://github.com/ggerganov/ggml/pull/585 - https://github.com/ggerganov/llama.cpp/issues/7773 Some projects/resources related to WebGPU: - https://eliemichel.github.io/LearnWebGPU/...
Stability AI has open-sourced their Audio/Sound generation model: [Stable Audio Open 1.0](https://huggingface.co/stabilityai/stable-audio-open-1.0). This would be a great addition to this library. Source Code: https://github.com/Stability-AI/stable-audio-tools