Vision 2
Open MLLM excelling in vision, reasoning, and long context via multimodal pre-training.
InternVL is an Open MLLM family (1B-78B) from OpenGVLab that excels at vision, reasoning, long context & agents via native multimodal pre-training. It outperforms base LLMs on text tasks.
PyTorch library for model interpretability across modalities.
Captum is a PyTorch library for model interpretability. It provides tools and techniques to understand and attribute the predictions of PyTorch models across various modalities, including vision and text. Captum supports most PyTorch models and allows for easy implementation and benchmarking of new interpretability algorithms.
