Instructions to use winglian/scout-qlora-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use winglian/scout-qlora-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("axolotl-quants/Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16") model = PeftModel.from_pretrained(base_model, "winglian/scout-qlora-adapter") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from winglian/scout-qlora-adapter: direct link, hf CLI and curl.
- Browser
- Download file 12 kB
-
https://huggingface.co/winglian/scout-qlora-adapter/resolve/main/training_args.bin
- Command line
-
hf download hf://winglian/scout-qlora-adapter/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/winglian/scout-qlora-adapter/resolve/main/training_args.bin
12 kB
- Xet hash:
- d05eb5b533d27e7c7417118312349eccbd10882fb82501e364f8ec9766942a75
- Size of remote file:
- 12 kB
- SHA256:
- 9f13ea91ea4b5dc7acf92da33df85eca7c2f53d25be0fab39b3b30aa671fc2c0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.