| license: cc-by-nc-sa-4.0 | |
| pipeline_tag: video-text-to-text | |
| # LITA model | |
| This repository contains the weights of the LITA-13B-v1.3 model, presented in the paper [LITA: Language Instructed Temporal-Localization Assistant](https://huggingface.co/papers/2403.19046). | |
| ## Usage | |
| See the Github repository: https://github.com/nvlabs/lita | |