Upload README.md with huggingface_hub

README.md

@@ -1,10 +1,47 @@
 ---
+datasets:
+- inaturalist2019
+language: en
 tags:
-- model_hub_mixin
-- pytorch_model_hub_mixin
+- image-classification
+- pytorch
+- efficientnet
+- mixture-of-experts
+- deepmoe
 ---
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Code: [More Information Needed]
-- Paper: [More Information Needed]
-- Docs: [More Information Needed]
+# DeepMoE EfficientNet-B0 fine-tuned on iNaturalist 2019
+
+This model is a Mixture-of-Experts (DeepMoE) variant of EfficientNet-B0, fine-tuned on the iNaturalist 2019 dataset to optimize both accuracy and computational efficiency (FLOP reduction).
+
+## Training Results
+- **Final Score (Acc/FLOPs composite)**: 83.2947
+- **Expert Activation Ratio**: 27.7%
+- **FLOPs Usage**: 53.3% *(compared to baseline B0)*
+- **Baseline B0 Reference FLOPs**: 388,184,000
+- **Total Runtime**: 5404.17 seconds
+
+## Hyperparameters
+- **Batch Size**: 256
+- **Gradient Accumulation Steps**: 4
+- **Weight Decay**: 0.005
+
+### Epochs
+- **Total Epochs**: 10
+  - Joint Training Epochs: 10
+  - Routing-Frozen Finetuning Epochs: 0
+
+### DeepMoE Architecture & Routing
+- **MoE Start Stage**: 1
+- **Latent Dimension**: 32
+- **Sparsity Penalty ($\lambda_g$)**: 0.0003
+- **Target Sparsity ($\mu$)**: 0.5
+- **ReLU Init (Val / Std)**: 1 / 1
+
+### Learning Rates
+- **MoE Routing Parameters**: 4.00e-02
+- **Classification Head**: 2.00e-02
+- **Base Model (Body)**: 2.00e-03
+- **Finetune Phase (Frozen Routing)**: 0.00e+00
+
+*Training was tracked using [Weights & Biases](https://wandb.ai).*