rryisthebest/First_Model
FIRST, developed by rryisthebest, is a 7 billion parameter language model fine-tuned from Zephyr-7B-β specifically for listwise reranking tasks. It leverages output logits to directly produce a ranked ordering of candidates, trained on an alphabetic version of the RankZephyr dataset derived from GPT-4 reorderings. This model excels at information retrieval and search result optimization, demonstrating superior performance across various reranking datasets on the BEIR benchmark.
Loading preview...
Overview
FIRST (Faster Improved Listwise Reranking with Single Token Decoding) is a 7 billion parameter language model, fine-tuned from the HuggingFaceH4/zephyr-7b-beta model. It is specifically designed for listwise reranking, utilizing the output logits of the first generated identifier to directly produce a ranked ordering of candidates. The model undergoes single-stage fine-tuning on a converted alphabetic version of the RankZephyr dataset, which includes RankGPT-4 reorderings of OpenAI's Ada2 orderings for 5,000 queries.
Key Capabilities
- Efficient Listwise Reranking: Optimizes the ordering of candidate lists by directly leveraging output logits.
- Superior Performance: Demonstrates leading performance on various reranking datasets within the BEIR benchmark, surpassing models like Rank Vicuna and Rank Zephyr.
- English Language Support: Primarily trained and optimized for English reranking tasks.
Good for
- Search Engine Optimization: Enhancing the relevance and order of search results.
- Information Retrieval Systems: Improving the ranking of documents or passages based on query relevance.
- Recommendation Systems: Reordering recommended items to present the most relevant options first.
For more technical details and evaluation results, refer to the associated paper and the GitHub repository.