Instructions to use ping98k/qwen3-8b-recall-writer-4e-2e4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ping98k/qwen3-8b-recall-writer-4e-2e4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ping98k/qwen3-8b-recall-writer-4e-2e4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
- Xet hash:
- 8322f441a9783fd6a4eff62f517e308989ab9e459bca5486f745039c781b3a72
- Size of remote file:
- 1.4 GB
- SHA256:
- 8dcbd1c742e486766f0a2156f59fd0170d83a0964550051c81107c54f6a4e0ce
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.