Upload README.md with huggingface_hub

README.md

@@ -78,7 +78,15 @@ The 13B model is trained on 32 A100 GPUs. The learning rate (LR) is controlled b
 
 ### Evaluation Results
 
-The evaluation results on the above benchmarks demonstrate the advantage of ProSparse, which is the only method achieving high sparsity and comparable performance to the original Swish-activated LLaMA2. Note that models under all settings are trained with the same number of tokens on the same mixed dataset. Refer to Section 4.2 of [paper](https://arxiv.org/pdf/2402.13516.pdf) for more details.
+The evaluation results on the above benchmarks demonstrate the advantage of ProSparse, which is the only method achieving high sparsity and comparable performance to the original Swish-activated LLaMA2. Note that models under all settings are trained with the same number of tokens on the same mixed dataset. Our evaluation is based on the framework [UltraEval](https://github.com/OpenBMB/UltraEval). The evaluation details are listed as follows:
+
+- **Code Generation**: We compute the average pass@1 scores on HumanEval (0-shot) and MBPP (3-shot).
+
+- **Commonsense Reasoning**: We report the average 0-shot perplexity (PPL) on PIQA, SIQA, HellaSwag, WinoGrande, and COPA.
+
+- **Reading Comprehension**: We compute the average 0-shot PPL on BoolQ, 0-shot accuracy on LAMBADA and TyDi QA.
+
+- **Other Popular Benchmarks**: We report the average accuracies on GSM8K (8-shot), MMLU (5-shot), Big Bench Hard (BBH) (3-shot), and the average PPL on AGI-Eval (0-shot).
 
 |        Setting        | Average<br>Sparsity | Code<br>Generation | Commonsense<br>Reasoning | Reading<br>Comprehension | GSM8K | MMLU  |  BBH  | AGI Eval | Average |
 | :-------------------: | :-----------------: | :----------------: | :----------------------: | :----------------------: | :---: | :---: | :---: | :---------: | :-----: |