Video-Text-to-Text
Transformers
Safetensors
English
KeyeVL1_5
feature-extraction
multimodal
custom_code
Eval Results
Instructions to use Kling-Keye-Official/Keye-VL-1_5-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kling-Keye-Official/Keye-VL-1_5-8B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kling-Keye-Official/Keye-VL-1_5-8B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Kwai-Keye commited on
Update model files
Browse files
README.md
CHANGED
|
@@ -455,8 +455,8 @@ See [evaluation/KC-MMBench/README.md](evaluation/KC-MMBench/README.md) for detai
|
|
| 455 |
|
| 456 |
|
| 457 |
<div align="center">
|
| 458 |
-
<img src="
|
| 459 |
-
<i> A SlowFast video
|
| 460 |
</div>
|
| 461 |
|
| 462 |
|
|
@@ -505,4 +505,4 @@ If you find our work helpful for your research, please consider citing our work.
|
|
| 505 |
|
| 506 |
## Acknowledgement
|
| 507 |
|
| 508 |
-
Kwai Keye-VL is developed based on the codebases of the following projects: [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384), [Qwen3](https://github.com/QwenLM/Qwen3), [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL), [VLMEvalKit](https://github.com/open-compass/VLMEvalKit). We sincerely thank these projects for their outstanding work.
|
|
|
|
| 455 |
|
| 456 |
|
| 457 |
<div align="center">
|
| 458 |
+
<img src="asset/slowfast.png" width="100%" alt="Kwai Keye Pretraining">
|
| 459 |
+
<i> A SlowFast video encoding demonstration: the Slow processes a smaller number of frames at higher resolution, while the Fast handles more frames at lower resolution.</i>
|
| 460 |
</div>
|
| 461 |
|
| 462 |
|
|
|
|
| 505 |
|
| 506 |
## Acknowledgement
|
| 507 |
|
| 508 |
+
Kwai Keye-VL is developed based on the codebases of the following projects: [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384), [Qwen3](https://github.com/QwenLM/Qwen3), [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL), [VLMEvalKit](https://github.com/open-compass/VLMEvalKit). We sincerely thank these projects for their outstanding work.
|