Update README.md

README.md

@@ -9,11 +9,15 @@ datasets:
 ---
 ## Introducation
 
-Sparse computing is increasingly recognized as an important direction to improve the computational efficiency of large language models (LLM).
+Sparse computing is increasingly recognized as an important direction to improve the computational efficiency (e.g., inference speed) of large language models (LLM).
 
-Recent studies ([Zhang el al., 2021](https://arxiv.org/abs/2110.01786); [Liu et al., 2023](https://openreview.net/pdf?id=wIPIhHd00i); [Mirzadeh et al., 2023](https://arxiv.org/abs/2310.04564)) reveal that LLMs inherently exhibit properties conducive to sparse computation when employing the ReLU activation function. This insight opens up new avenues for model efficiency, akin to MoE's selective activation. By dynamically choosing model parameters for computation, we can substantially boost efficiency.
+Recent studies ([Zhang el al., 2021](https://arxiv.org/abs/2110.01786); [Liu et al., 2023](https://openreview.net/pdf?id=wIPIhHd00i); [Mirzadeh et al., 2023](https://arxiv.org/abs/2310.04564)) reveal that LLMs inherently exhibit properties conducive to sparse computation when employing the ReLU activation function.
+This insight opens up new avenues for inference speed, akin to MoE's selective activation.
+By dynamically choosing model parameters for computation, we can substantially boost inference speed.
 
-However, the widespread adoption of ReLU-based models in the LLM field remains limited. Here we introduce a new 7B ReLU-based LLM, Bamboo(Github link:[https://github.com/SJTU-IPADS/Bamboo](https://github.com/SJTU-IPADS/Bamboo)), which boasts nearly 85% sparsity and performance levels on par with [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1).
+However, the widespread adoption of ReLU-based models in the LLM field remains limited.
+Here we introduce a new 7B ReLU-based LLM, Bamboo(Github link:[https://github.com/SJTU-IPADS/Bamboo](https://github.com/SJTU-IPADS/Bamboo)),
+which boasts nearly 85% sparsity and performance levels on par with [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1).
 
 ## Model Architecture
 
@@ -75,9 +79,10 @@ Our evaluation is based on the framework lm-evaluation-harness and opencompass.
 | Ours    | 0.6389 | 0.7593     | 0.4406     | 0.8217    | 0.5315 | 0.6195 | 0.256     |      |         |
 | Mistral | 0.6265 | 0.7924     | 0.4262     | 0.8332    | 0.4018 | 0.6143 | 0.2621    |      |         |
 
-## Speed Evaluation Results
+## Inference Speed Evaluation Results
 
-We utilize [PowerInfer](https://arxiv.org/pdf/2312.12456.pdf), a state-of-the-art acceleration framework leveraging activation sparsity. Here we show the inference speed compared with llama.cpp/transformers.
+We utilize [PowerInfer](https://arxiv.org/pdf/2312.12456.pdf), a state-of-the-art acceleration framework leveraging activation sparsity.
+Here we show the inference speed compared with llama.cpp/transformers.
 
 ## Limitation & Disclaimer