Sherlock
Collection
Series model of paper "Sherlock: Self-Correcting Reasoning in Vision-Language Models" • 5 items • Updated
• 3
Sherlock: Self-Correcting Reasoning in Vision-Language Models
Introduction
Sherlock is a training framework focus on improving Vision-Language Models reasoning and self-correction capabilities.
GitHub repo: https://github.com/DripNowhy/Sherlock
Project Page: https://dripnowhy.github.io/Sherlock/
- Downloads last month
- -
Model tree for Tuwhy/Llama-3.2V-11B-Sherlock-iter1
Base model
meta-llama/Llama-3.2-11B-Vision-Instruct