We introduce Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. Preliminary evaluation using GPT-4 as a judge shows Vicuna-13B achieves more than 90%* quality of OpenAI ChatGPT and Google Bard while outperforming other models like LLaMA and Stanford Alpaca in more than 90%* of cases. The cost of training Vicuna-13B is around $300. The code and weights, along with an online demo, are publicly available for non-commercial use.
An interesting question arose at a recent xAPI Camp hosted by The eLearning Guild: “What happened to objectives in xAPI?” We should be able to use xAPI to document successful completion of eLearning, but without statements of learning objectives in the content, this is not possible.
Game Learning Analytics (GLA) is the process of applying Learning Analytics techniques to Serious Games in order to get insight about how the game is being used and improve the educational experience.
Recommender systems provide users with content they might be interested in. Conventionally, recommender systems are evaluated mostly by using prediction accuracy metrics only. But, the ultimate goal of a recommender system is to increase user satisfaction.
J. Turian, L. Ratinov, and Y. Bengio. Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, page 384--394. Stroudsburg, PA, USA, Association for Computational Linguistics, (2010)
N. Dahlbäck, A. Jönsson, and L. Ahrenberg. IUI '93: Proceedings of the 1st international conference on Intelligent user interfaces, page 193--200. New York, NY, USA, ACM, (1993)