Video-Text-to-Text
Transformers
Safetensors
English
KeyeVL1_5
feature-extraction
multimodal
custom_code
Instructions to use Kwai-Keye/Keye-VL-1_5-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kwai-Keye/Keye-VL-1_5-8B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kwai-Keye/Keye-VL-1_5-8B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Improve model card with abstract summary and GitHub link
#3
by nielsr HF Staff - opened
This PR enhances the model card for Kwai Keye-VL 1.5 by:
- Updating the main title to "Kwai Keye-VL 1.5" for better precision, aligning with the paper and news.
- Adding a concise summary of the model's key innovations and capabilities, derived from the paper's abstract, to provide an immediate overview for users.
- Integrating a direct link to the official GitHub repository (
https://github.com/Kwai-Keye/Keye) in the prominent initial links section, improving code discoverability. - Correcting the typo "Technique Report" to "Technical Report" in the introductory links.
All existing metadata, code snippets, and other detailed content remain unchanged to preserve functionality and user experience.
Kwai-Keye changed pull request status to merged