Training and Finetuning Reranker Models with Sentence Transformers v4
huggingface.co · 5,124 words · saved by 1 readers
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Sentence Transformers is a Python library for using and training embedding and reranker models for a wide range of applications, such as retrieval augmented generation, semantic search, semantic textual similarity, paraphrase mining, and more. In this blogpost, I'll show you how to use it to finetune a reranker model (also known as a cross-encoder) that beats all existing options on exactly your data. This method can also train extremely strong new reranker models from scratch. Finetuning reranker models involves several components: datasets, loss functions, training arguments, evaluators,…
saved by
related reading
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- Composer2.pdfcursor.com
- Tinkerthinkingmachines.ai
- The Annotated Transformernlp.seas.harvard.edu
- Rerankers and Two-Stage Retrieval | Pineconepinecone.io
- Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com
- Trainer · Hugging Facehuggingface.co
- Hugging Face · GitHubgithub.com
- 1810.04805arxiv.org
- Generalized Language Models | Lil'Loglilianweng.github.io
- Fine-tuning, Check! · Hugging Facehuggingface.co
- Fine-tuning a model with the Trainer API · Hugging Facehuggingface.co