Instructions to use RyanJT/trained-quant-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use RyanJT/trained-quant-8bit with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("RyanJT/quantized-granite-4bit-3b-code-instruct") model = PeftModel.from_pretrained(base_model, "RyanJT/trained-quant-8bit") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- fc3d4be2843f373c4ff5ecada7cfa10b1a6fff8f36444b0486f6ef0b2b39f327
- Size of remote file:
- 5.05 kB
- SHA256:
- ab7b368eea2e97d01a37aafe8c89d5063dbb7667b9ef9ba8a87e991eb756c741
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.