---
license: apache-2.0
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

The 13B model of "SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens"

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Developed by:** ainergy
- **Language(s) (NLP):** Code
- **Finetuned from model:** CodeLlama-13B

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/ainergy-ml/SDSAT
- **Paper:** https://arxiv.org/abs/2403.18647


## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Results

![image/png](https://cdn-uploads.huggingface.co/production/uploads/66062eb73b0163cbee095429/ufANs_jAkd8Y_nBl1IrRQ.png)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/66062eb73b0163cbee095429/7bLQz2Uzd8DSnD4ADgPUJ.png)

### Walltime improvement

![image/png](https://cdn-uploads.huggingface.co/production/uploads/66062eb73b0163cbee095429/XxKRg_2Qgwq8j44DEUHDq.png)