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")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("poolside-laguna-hackathon/laguna-vision", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Bootstrap Laguna runtime after endpoint startup
Browse files- requirements.txt +6 -6
requirements.txt
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
-
accelerate==1.
|
| 2 |
bitsandbytes==0.49.2
|
| 3 |
-
huggingface_hub==
|
| 4 |
-
peft==0.
|
| 5 |
-
pillow==
|
| 6 |
requests>=2.31
|
| 7 |
-
safetensors==0.
|
| 8 |
-
transformers[audio,sentencepiece,sklearn,vision]==
|
|
|
|
| 1 |
+
accelerate==1.6.0
|
| 2 |
bitsandbytes==0.49.2
|
| 3 |
+
huggingface_hub[hf_transfer]==0.30.2
|
| 4 |
+
peft==0.15.1
|
| 5 |
+
pillow==11.3.0
|
| 6 |
requests>=2.31
|
| 7 |
+
safetensors==0.5.3
|
| 8 |
+
transformers[audio,sentencepiece,sklearn,vision]==4.51.3
|