Instructions to use poolside-laguna-hackathon/laguna-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use poolside-laguna-hackathon/laguna-vision 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="poolside-laguna-hackathon/laguna-vision")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("poolside-laguna-hackathon/laguna-vision", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -41,4 +41,4 @@ This is an experimental checkpoint intended to verify that Laguna can condition
|
|
| 41 |
- Early checkpoint quality may be uneven.
|
| 42 |
- OCR, counting, and spatial localization can fail.
|
| 43 |
- The adapter depends on the Laguna Vision inference/training code in this repository layout.
|
| 44 |
-
- Generated text may hallucinate; validate outputs before relying on
|
|
|
|
| 41 |
- Early checkpoint quality may be uneven.
|
| 42 |
- OCR, counting, and spatial localization can fail.
|
| 43 |
- The adapter depends on the Laguna Vision inference/training code in this repository layout.
|
| 44 |
+
- Generated text may hallucinate; validate outputs before relying on them.
|