Update README
Browse files
README.md
CHANGED
@@ -19,6 +19,10 @@ python eval.py --model_path <path to model>
|
|
19 |
|
20 |
Refer to our [code repository](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/Mamba-Shedder) for the environment information to run this command.
|
21 |
|
|
|
|
|
|
|
|
|
22 |
## Model Sources
|
23 |
|
24 |
- **Repository:** [https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/Mamba-Shedder](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/Mamba-Shedder)
|
@@ -27,10 +31,21 @@ Refer to our [code repository](https://github.com/IntelLabs/Hardware-Aware-Autom
|
|
27 |
## Citation
|
28 |
|
29 |
```bibtex
|
30 |
-
@
|
31 |
title = {Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models},
|
32 |
-
author = {J. Pablo
|
33 |
-
|
34 |
-
|
|
|
|
|
|
|
|
|
35 |
}
|
36 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
Refer to our [code repository](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/Mamba-Shedder) for the environment information to run this command.
|
21 |
|
22 |
+
## Ethical Considerations
|
23 |
+
|
24 |
+
Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.
|
25 |
+
|
26 |
## Model Sources
|
27 |
|
28 |
- **Repository:** [https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/Mamba-Shedder](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/Mamba-Shedder)
|
|
|
31 |
## Citation
|
32 |
|
33 |
```bibtex
|
34 |
+
@inproceedings{munoz2025mambashedder,
|
35 |
title = {Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models},
|
36 |
+
author = {Mu{\~n}oz, J. Pablo and Yuan, Jinjie and Jain, Nilesh},
|
37 |
+
booktitle = "Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)",
|
38 |
+
month = jun,
|
39 |
+
year = "2025",
|
40 |
+
address = "Albuquerque, New Mexico",
|
41 |
+
publisher = "Association for Computational Linguistics",
|
42 |
+
url = "",
|
43 |
}
|
44 |
```
|
45 |
+
|
46 |
+
### Original Work Citation
|
47 |
+
This work builds upon work done by the State-Spaces team. Please see the following for additional citations of their work:
|
48 |
+
|
49 |
+
**Repository:** ([state-spaces/mamba](https://github.com/state-spaces/mamba)
|
50 |
+
**Paper:** [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://arxiv.org/abs/2312.00752)
|
51 |
+
|