Instructions to use windgrin/q2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use windgrin/q2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/data/LLM/Llama-3.2-11B-Vision-Instruct") model = PeftModel.from_pretrained(base_model, "windgrin/q2") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from windgrin/q2: direct link, hf CLI and curl.
- Browser
- Download file 839 MB
-
https://huggingface.co/windgrin/q2/resolve/main/optimizer.pt
- Command line
-
hf download hf://windgrin/q2/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/windgrin/q2/resolve/main/optimizer.pt
839 MB
- Xet hash:
- 64a535972cd370c337b6db944561d08d0ebdfe585605903e8212b904fc334e0b
- Size of remote file:
- 839 MB
- SHA256:
- c8ae7e4b0324900975685870581db46ff53f032eb0add82bbb11094d2477c3d0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.