LocalAI supports running HuggingFace and GGUF embedding models on CPU and GPU. It can be configured independently of the LocalAI LLM settings and run concurrently. Modify the model at any time in Settings.
LocalAI supports running HuggingFace and GGUF embedding models on CPU and GPU. It can be configured independently of the LocalAI LLM settings and run concurrently. Modify the model at any time in Settings.