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
Download tokenizer.json from joermd/speedy_think: direct link, hf CLI and curl.
- Browser
- Download file 17.2 MB
-
https://huggingface.co/joermd/speedy_think/resolve/b4526ccc9f90b1bcac21fe3ce44fbb32fd47326e/tokenizer.json
- Command line
-
hf download hf://joermd/speedy_think@b4526ccc9f90b1bcac21fe3ce44fbb32fd47326e/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/joermd/speedy_think/resolve/b4526ccc9f90b1bcac21fe3ce44fbb32fd47326e/tokenizer.json
17.2 MB
- Xet hash:
- 85ad5c8944ff5c073c022c58ae980d26c3527c588935c913dd82f733e95103c6
- Size of remote file:
- 17.2 MB
- SHA256:
- d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.