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
Update endpoint docs and runtime dependency pins
Browse files- requirements.txt +7 -8
requirements.txt
CHANGED
|
@@ -1,9 +1,8 @@
|
|
| 1 |
-
accelerate
|
| 2 |
-
bitsandbytes
|
| 3 |
-
huggingface_hub
|
| 4 |
-
peft
|
| 5 |
-
pillow
|
| 6 |
requests>=2.31
|
| 7 |
-
safetensors
|
| 8 |
-
|
| 9 |
-
transformers>=4.44
|
|
|
|
| 1 |
+
accelerate==1.13.0
|
| 2 |
+
bitsandbytes==0.49.2
|
| 3 |
+
huggingface_hub==1.17.0
|
| 4 |
+
peft==0.18.1
|
| 5 |
+
pillow==12.2.0
|
| 6 |
requests>=2.31
|
| 7 |
+
safetensors==0.7.0
|
| 8 |
+
transformers==5.9.0
|
|
|