Ida Silfverskiöld

Working with Retrieval Using techniques to improve semantic search Ida Silfverskiöld · Follow Published in Towards Data Science · 17 min read · 2 hours ago — Demonstration of clustering before performing semantic search | Image by author If you’re not a member but want to read this article, see this friend link here. Embeddings are a cornerstone of natural language processing. You can do quite a lot with embeddings, but one of the more

Using Microsoft’s Phi-3 to generate synthetic data Ida Silfverskiöld · Follow Published in Towards Data Science · 17 min read · 7 hours ago — Build a smaller model from a bigger model to perform on a use case | Image by author Text classification models aren’t new, but the bar for how quickly they can be built and how well they perform has improved. The transformer-based model I will fine-tune here is more than