akjindal53244/Llama-3.1-Storm-8B

Llama-3.1-Storm-8B is an 8 billion parameter language model developed by Ashvini Kumar Jindal, Pawan Kumar Rajpoot, Ankur Parikh, and Akshita Sukhlecha, built upon Meta AI's Llama-3.1-8B-Instruct with a 32768 token context length. This model significantly outperforms its base and Hermes-3-Llama-3.1-8B across diverse benchmarks, excelling in instruction following, knowledge-driven QA, reasoning, and function calling. It achieves these enhancements through self-curation, Spectrum-based targeted fine-tuning, and SLERP model merging, making it a powerful generalist model for various applications.