Instructions to use SparseLLM/swiglu-80B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SparseLLM/swiglu-80B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SparseLLM/swiglu-80B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 7d2923dbfbe5218d421c0f1cac1725e7331901d8f8a2e20ed92e5fed1ab998e9
- Size of remote file:
- 967 Bytes
- SHA256:
- 747ec99bae3fd9d7bf9c3b9172e5ca0d82ca0d23d64a58ef1752b612f196817b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.