Instructions to use Firoj112/KVASIR_4bit_quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Firoj112/KVASIR_4bit_quantized with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/root/.cache/modelscope/hub/models/google/paligemma-3b-pt-224") model = PeftModel.from_pretrained(base_model, "Firoj112/KVASIR_4bit_quantized") - Notebooks
- Google Colab
- Kaggle
File size: 133 Bytes
04e0ec4 | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:172fab587d68c56b63eb3620057c62dfd15e503079ff7fce584692e3fd5bf4da
size 34600820
|