TeapotLLM- an open-source <1B model for hallucination-resistant Q&A on a CPU
(huggingface.co)
Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs. Teapot is trained to only answer using context from documents, reducing hallucinations. Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction. Teapot is a model built by and for the community.
Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs. Teapot is trained to only answer using context from documents, reducing hallucinations. Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction. Teapot is a model built by and for the community.