|
--- |
|
license: mit |
|
--- |
|
Model details |
|
Model type: LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. |
|
|
|
Model date: LLaVA-flint-v0.5-1B was trained in Nov 2023. |
|
|
|
|
|
This model is an implementation of Llava using the TinyLlama 1.1b as the frozen llm model |
|
|
|
It's designed to be able to run in low-resource environments |
|
We plan to release further versions designed for specific tasks so stay tuned. |
|
|
|
|
|
Paper or resources for more information on the original Llava: https://llava-vl.github.io/ |
|
|
|
License |
|
Apache 2 (TinyLlama) |
|
Where to send questions or comments about the model: ask me here on huggingface :) |
|
|
|
Intended use |
|
Primary intended uses: The primary use of LLaVA 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 |
|
558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP. |
|
158K GPT-generated multimodal instruction-following data. |
|
450K academic-task-oriented VQA data mixture. |
|
40K ShareGPT data. |
|
Evaluation dataset |
|
A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs. |
|
|
|
|
|
|
|
|
