Update README.md

README.md

@@ -3,9 +3,34 @@ language: en
 license: apache-2.0
 ---
 
-# Mamba-Shedder Model: mamba-shedder-mamba2-2.7b-ssm22
+# Mamba-Shedder Model: Mamba-Shedder-Mamba-2.2B
 
-| Source Model                                                       | Components Removed                     | Recovery Tuning | WikiText PPL | Avg. Score | Relative Acc. |
-|--------------------------------------------------------------------|-----------------------------------------|-----------------|---------------|------|------|
-| [mamba2-2.7b](https://huggingface.co/state-spaces/mamba2-2.7b)       |  -                                      | -               | 4.10 | 60.2 | 100%          |
-| [mamba-shedder-mamba2-2.7b-ssm22](https://huggingface.co/IntelLabs/mamba-shedder-mamba2-2.7b-ssm22)       |  22 SSDs                        | ✘               | 6.50 | 57.8 | 96%           |
+- Base Model: [state-spaces/mamba2-2.7b](https://huggingface.co/state-spaces/mamba2-2.7b)
+- Pruned Components: **22 SSDs** (Layer 63, 54, 42, 45, 53, 57, 58, 59, 38, 56, 50, 61, 60, 43, 37, 62, 49, 34, 55, 33, 39, 35)
+- Recovery Tuning: No
+
+### Evaluation
+
+```bash
+git clone https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.git
+cd Mamba-Shedder
+python eval.py --model_path <path to model>
+```
+
+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.
+
+## Model Sources
+
+- **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)
+- **Paper:** [Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models]()
+
+## Citation
+
+```bibtex
+@article{munoz2025mambashedder,
+  title = {Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models},
+  author = {J. Pablo Munoz and Jinjie Yuan and Nilesh Jain},
+  journal = {},
+  year = {2025}
+}
+```