Instructions to use joermd/speedy_think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use joermd/speedy_think with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("joermd/speedy_think", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
- Xet hash:
- a22bf55b6392efc9e368b2c5a567383a477698b4d2d495a15d8ba3672374ca52
- Size of remote file:
- 168 MB
- SHA256:
- 8bf85bd0b927616c709f777c7f110971ab9a51b2f12992bf4bfb00ac9ee41b38
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.