Instructions to use MaestroYan/JEMM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use MaestroYan/JEMM with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.8-27B") model = PeftModel.from_pretrained(base_model, "MaestroYan/JEMM") - Notebooks
- Google Colab
- Kaggle
Download assets/latency.png from MaestroYan/JEMM: direct link, hf CLI and curl.
- Browser
- Download file 243 kB
-
https://huggingface.co/MaestroYan/JEMM/resolve/main/assets/latency.png
- Command line
-
hf download hf://MaestroYan/JEMM/assets/latency.png
-
curl -L -o latency.png https://huggingface.co/MaestroYan/JEMM/resolve/main/assets/latency.png
243 kB

- Xet hash:
- 89bf505a459f44d62136d39d16380665c3102b95564c63bc52a7cf5202b1dd44
- Size of remote file:
- 243 kB
- SHA256:
- e6ff6a028ef370ae4809df8e3f06df5d1922e4105f4e217d88aacd30ac6b6115
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.