Image-to-Text
Transformers
Safetensors
English
blip-2
text-generation
video-to-text
video-captioning
image-captioning
visual-question-answering
Instructions to use kpyu/eilev-blip2-flan-t5-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kpyu/eilev-blip2-flan-t5-xl with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="kpyu/eilev-blip2-flan-t5-xl")# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("kpyu/eilev-blip2-flan-t5-xl") model = AutoModelForSeq2SeqLM.from_pretrained("kpyu/eilev-blip2-flan-t5-xl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update demo link
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ EILEV BLIP-2-Flan-T5-xl is a VLM optimized for egocentric video. It can perform
|
|
| 28 |
|
| 29 |
- **Repository:** https://github.com/yukw777/EILEV
|
| 30 |
- **Paper:** https://arxiv.org/abs/2311.17041
|
| 31 |
-
- **Demo:** https://
|
| 32 |
|
| 33 |
## Bias, Risks, and Limitations
|
| 34 |
|
|
|
|
| 28 |
|
| 29 |
- **Repository:** https://github.com/yukw777/EILEV
|
| 30 |
- **Paper:** https://arxiv.org/abs/2311.17041
|
| 31 |
+
- **Demo:** https://2e09-141-212-106-177.ngrok-free.app
|
| 32 |
|
| 33 |
## Bias, Risks, and Limitations
|
| 34 |
|