Instructions to use CreatorPhan/Q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use CreatorPhan/Q8 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("vilm/vietcuna-3b") model = PeftModel.from_pretrained(base_model, "CreatorPhan/Q8") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- fa1d5c310b8a35b0d112455d1200ee912bf48b424589ab5ba340077f06d1bf5f
- Size of remote file:
- 78.8 MB
- SHA256:
- 6d448191017e2f69fbf0d482658b18644166bfe4e5872511455b4a160de0a0cd
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.