LVIS-INSTRUCT4V
Visual Instructions
A dataset of fine-grained visual instructions generated by prompting a large language model with images from another dataset
131 stars
3 watching
0 forks
last commit: 11 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 xuefuzhao/instructionwild | Creating a large-scale user-based instruction dataset for natural language processing research and development | 453 |
 flagopen/flaginstruct | A collection of diverse instruction corpora for improving the development and tuning of Chinese Language Models | 173 |
 vt-nlp/multiinstruct | A multimodal benchmark dataset designed to evaluate the performance of vision-language foundation models through instruction tuning. | 133 |
 orhonovich/unnatural-instructions | A collection of automatically generated instructions for training language models. | 175 |
 jy0205/lavit | A unified framework for training large language models to understand and generate visual content | 528 |
 rucaibox/comvint | Creating synthetic visual reasoning instructions to improve the performance of large language models on image-related tasks | 18 |
 salt-nlp/llavar | An open-source project that enhances visual instruction tuning for text-rich image understanding by integrating GPT-4 models with multimodal datasets. | 258 |
 ffxsam/vue-typescript-cookbook | A cookbook and resource guide for developers learning Vue.js with TypeScript | 273 |
 pvit-official/pvit | A project that extends large language models by integrating an additional region-level vision encoder to improve visual instruction tuning. | 36 |
 ncsoft/cap2qa | A dataset and implementation of a method to generate instructions based on visual data | 5 |
 aidc-ai/parrot | A method and toolkit for fine-tuning large language models to perform visual instruction tasks in multiple languages. | 30 |
 vefstathiou/so_word2vec | This is a word embedding model trained on Stack Overflow posts for use in natural language processing tasks. | 40 |
 alexcode/vue2vis | A Vue.js wrapper for the popular visualization library Visjs, allowing developers to easily integrate 2D and 3D graphing capabilities into their web applications. | 217 |
 freedomintelligence/allava | A collection of datasets and models designed to support the training of lite vision-language models. | 246 |
 vlf-silkie/vlfeedback | An annotated preference dataset and training framework for improving large vision language models. | 85 |