Instructions to use google/deplot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/deplot with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="google/deplot")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/deplot") model = AutoModelForMultimodalLM.from_pretrained("google/deplot", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Difficulty in Reproducing Results on PlotQA Test Set
#18 opened about 1 year ago
by
seven-night
how to use cuda
😎 1
2
#17 opened about 2 years ago
by
susht
HTTPSConnectionPool(host='huggingface.co', port=443): M
2
#16 opened over 2 years ago
by
Henry96
How to extract data inbetween points
#15 opened over 2 years ago
by
Vuks
Can Deplot model evaluate with BLEU and BLEURT ?
#13 opened over 2 years ago
by
jpjp9292
Loss Function Configuration
#10 opened about 3 years ago
by
DoctorSlimm
Adding ONNX file of this model
#8 opened about 3 years ago
by
ashwinR
Is there a way to make this model run faster ?
👍 4
#5 opened over 3 years ago
by
arungautham
Update preprocessor_config.json
1
#4 opened over 3 years ago
by
owaiskha9654
"is_vqa"=True in preprocessor? Is this correct?
2
#2 opened over 3 years ago
by
RainbowMan1