Update README.md

README.md

@@ -49,7 +49,7 @@ language:
 <a href="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue" alt="license"></a>
 <a href="https://arxiv.org/abs/2412.17743" target="_blank"><img src=https://img.shields.io/badge/arXiv-b5212f.svg?logo=arxiv></a>
 <a href="https://huggingface.co/collections/yulan-team/yulan-mini-676d214b24376739b00d95f3"><img alt="Static Badge" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-blue?color=8A2BE2"></a>
-<a><img src="https://img.shields.io/github/stars/RUC-GSAI/YuLan-Mini"></a>
+<a href="https://github.com/RUC-GSAI/YuLan-Mini" target="_blank"><img src="https://img.shields.io/github/stars/RUC-GSAI/YuLan-Mini"></a>
 </div>
 
 YuLan-Mini is a lightweight language model with 2.4 billion parameters. It achieves performance comparable to industry-leading models trained on significantly more data, despite being pre-trained on only 1.08T tokens. The model excels particularly in the domains of **mathematics** and **code**. To facilitate reproducibility, we will open-source the relevant pre-training resources.
@@ -144,7 +144,7 @@ Optimizer states before annealing will be released in a future update.
 
 <details><summary>5. Data Distribution for every phase</summary>
 
-<a href="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/pretrain/final.pdf">High-Definition Image</a>
+<a href="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/pretrain/final.pdf">High-resolution version</a>
 
 <a href="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/pretrain/final.pdf">
   <div align=center>
@@ -171,6 +171,14 @@ The synthetic data we are using is released in <a href="https://huggingface.co/c
 Intermediate optimizer states will be released in a future update.
 </details>
 
+### What you can do with these pre-training resources
+
+1. **Pre-train** your own LLM. You can use our data and curriculum to train a model that's just as powerful as YuLan-Mini.
+2. Perform your own **learning rate annealing**. During the annealing phase, YuLan-Mini's learning ability is at its peak. You can resume training from the checkpoint before annealing and use your own dataset for learning rate annealing.
+3. **Fine-tune** the Instruct version of the LLM. You can use the YuLan-Mini base model to train your own Instruct version.
+4. **Training dynamics** research. You can use YuLan-Mini's intermediate checkpoints to explore internal changes during the pre-training process.
+5. **Synthesize** your own data. You can use YuLan-Mini's data pipeline to clean and generate your own dataset.
+
 ---
 
 ## Quick Start 💻
@@ -200,6 +208,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 vllm serve yulan-team/YuLan-Mini --dtype bfloat16
 ```
 
+**SGLang Serve Example**
+```bash
+python -m sglang.launch_server --model-path yulan-team/YuLan-Mini --port 30000 --host 0.0.0.0
+```
 
 ---