DLYuanGod/TinyGPT-V
An efficient multimodal large language model using small backbones for text and image processing.
Not currently ranked — collecting fresh signals.
star history
TinyGPT-V is an efficient multimodal LLM that processes both text and images using compact backbone architectures. The project provides training code, pretrained model weights on HuggingFace, and interactive demo spaces for model evaluation. According to the authors, it achieves approximately 98% of InstructBLIP’s performance while using smaller model components.
Frequently asked
- What is DLYuanGod/TinyGPT-V?
- An efficient multimodal large language model using small backbones for text and image processing.
- Is TinyGPT-V open source?
- Yes — DLYuanGod/TinyGPT-V is open source, released under the BSD-3-Clause license.
- What language is TinyGPT-V written in?
- DLYuanGod/TinyGPT-V is primarily written in Python.
- How popular is TinyGPT-V?
- DLYuanGod/TinyGPT-V has 1.3k stars on GitHub.
- Where can I find TinyGPT-V?
- DLYuanGod/TinyGPT-V is on GitHub at https://github.com/DLYuanGod/TinyGPT-V.