Instructions to use Gavin-chen/Qwen-Compress with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gavin-chen/Qwen-Compress with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Gavin-chen/Qwen-Compress", device_map="auto") - Notebooks
- Google Colab
- Kaggle
bro you should upload this to github immediately this could be a trend
#1
by llmguy342 - opened
everyone uses qwen models it could be great to see this with a qwen model
Appreciate the encouragement! Right now, the completion level is still too low to release on GitHub. It really requires Continual Pre-Training (CPT) to be viable, which is currently out of reach due to budget constraints.
If you have the compute resources and wants to try CPT on it, feel free to reach out!
I would love to but my pc is not that powerful...