Update README.md

README.md

@@ -2,12 +2,21 @@
 language: en
 tags:
 - pythae
+- reproducibility
 license: apache-2.0
 ---
 
-### Downloading this model from the Hub
 This model was trained with pythae. It can be downloaded or reloaded using the method `load_from_hf_hub`
 ```python
 >>> from pythae.models import AutoModel
->>> model = AutoModel.load_from_hf_hub(hf_hub_path="your_hf_username/repo_name")
+>>> model = AutoModel.load_from_hf_hub(hf_hub_path="clementchadebec/reproduced_piwae")
 ```
+
+## Reproducibility
+This trained model reproduces the results of the official implementation of [1].
+
+| Model | Dataset | Metric | Obtained value | Reference value |
+|:---:|:---:|:---:|:---:|:---:|
+| PIWAE (M=8, K=8) | Dyn. Binarized MNIST | NLL (5000 IS) | 84.58 (0.00) | 84.46 (0.06) |
+
+[1] Rainforth, Tom, et al. "Tighter variational bounds are not necessarily better." International Conference on Machine Learning. PMLR, 2018.