Instructions to use JunlongTong/StreamingLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JunlongTong/StreamingLLM with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("JunlongTong/StreamingLLM", device_map="auto") - Notebooks
- Google Colab
- Kaggle

- Xet hash:
- 19b691b8191f52de979feb5723c9b73eca70e5a247f29d43a9b28db9b8fc910d
- Size of remote file:
- 640 kB
- SHA256:
- c8196f32abaf8d72b1b6e9ecae41d11014bec1300b702f3bb3b1ee8daf8e343b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.