Instructions to use SparseLLM/prosparse-llama-2-13b-predictor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SparseLLM/prosparse-llama-2-13b-predictor with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="SparseLLM/prosparse-llama-2-13b-predictor", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SparseLLM/prosparse-llama-2-13b-predictor", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -19,5 +19,7 @@ Please kindly cite using the following BibTeX:
|
|
| 19 |
title={{ProSparse}: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models},
|
| 20 |
author={Song, Chenyang and Han, Xu and Zhang, Zhengyan and Hu, Shengding and Shi, Xiyu and Li, Kuai and Chen, Chen and Liu, Zhiyuan and Li, Guangli and Yang, Tao and Sun, Maosong},
|
| 21 |
year={2024},
|
|
|
|
|
|
|
| 22 |
}
|
| 23 |
```
|
|
|
|
| 19 |
title={{ProSparse}: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models},
|
| 20 |
author={Song, Chenyang and Han, Xu and Zhang, Zhengyan and Hu, Shengding and Shi, Xiyu and Li, Kuai and Chen, Chen and Liu, Zhiyuan and Li, Guangli and Yang, Tao and Sun, Maosong},
|
| 21 |
year={2024},
|
| 22 |
+
journal={arXiv preprint arXiv:2402.13516},
|
| 23 |
+
url={https://arxiv.org/pdf/2402.13516.pdf}
|
| 24 |
}
|
| 25 |
```
|