Instructions to use sarvamai/shuka-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sarvamai/shuka-1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sarvamai/shuka-1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
self.processor turning out to be None in ShukaPipeline __init__()
#11
by DankDuck1 - opened
I am following the demo code given in the repo. It seems easy. However, I am getting an error in class ShukaPipeline in function preprocess on line
text = self.processor.tokenizer.apply_chat_template(
turns, add_generation_prompt=True, tokenize=False
)
On debugging the error, I found that self.processor is None and is not being set up properly in init().
You can follow the above code in repo main page to reproduce the error. I am using free environment of Google Colab. Please see!
DankDuck1 changed discussion status to closed
DankDuck1 changed discussion status to open