SESAME
Collection
Official checkpoints of the paper -- See, Say, Segment: Teaching LMMs to Overcome False Premises (SESAME), CVPR 2024.
•
2 items
•
Updated
SESAME
- Model type: SESAME is an open-source multimodal model trained by fine-tuning LLaVA on various instruction-based image grounding (segmentation) data. It is an auto-regressive language model plus a segmentation model.
- Paper or resources for more information: https://see-say-segment.github.io/
- Where to send questions or comments about the model: https://github.com/see-say-segment/sesame/issues
- Intended use
- Primary intended uses: The primary use of SESAME is research on large multimodal models and chatbots.
- Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
- Training dataset: (FP-/R-)RefCOCO(+/g) + LLaVA 150K VQA data
- Downloads last month
- 46
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.