oumi-ai/HallOumi-8B

HallOumi-8B by oumi-ai is an 8 billion parameter hallucination detection model, fine-tuned from Llama-3.1-8B-Instruct, with a 32768 token context length. It specializes in per-sentence verification of content, providing support determinations, confidence scores, relevant citations, and human-readable explanations. This model is optimized for building trust in AI systems by verifying outputs against known contexts, outperforming larger models like DeepSeek R1 and Claude Sonnet 3.5 in F1 score for hallucination detection.