Add metadata and link to the paper and code

README.md

@@ -1,13 +1,20 @@
+---
+pipeline_tag: text-generation
+library_name: transformers
+---
+
 ## Introduction
 MetaStone-L1 is the lite reasoning model of the MetaStone series, which aims to enhance the performance in hard downstream tasks.
 
 On core reasoning benchmarks including mathematics and code, MetaStone-L1-7B achieved SOTA results in the parallel-level models, and it also achieved the comparable results as the API models such as Claude-3.5-Sonnet-1022 and GPT4o-0513.
 <img src="./introduction.png" alt="Logo" width="800">
 
-This repo contains the MetaStone-L1-7B model, which is trained based on DeepSeek-R1-Distill-Qwen-7B by GRPO. For full details of this model please refer to our release blog.
+This repo contains the MetaStone-L1-7B model, which is trained based on DeepSeek-R1-Distill-Qwen-7B by GRPO. For full details of this model please refer to our release blog. The model was presented in [A Graph-Based Synthetic Data Pipeline for Scaling High-Quality Reasoning Instructions](https://huggingface.co/papers/2412.08864).
+
+Code: https://github.com/Jayce1kk/GSDP
 
 ## Requirements
-We advise you to use the latest version of transformers(```transformers==4.48.3```).  For the best experience, please review the [Usage Guidelines](#usage-guidelines).
+We advise you to use the latest version of transformers(```transformers==4.48.3```). For the best experience, please review the [Usage Guidelines](#usage-guidelines).
 
 ## Quickstart
 Here give the example of how to use our model.
@@ -20,7 +27,9 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
 messages = [
-    {"role": "user", "content": "Complete the square for the following quadratic: $-x^2+7 x-11$\n\nPlease reason step by step, and put your final answer within \\boxed{}."}
+    {"role": "user", "content": "Complete the square for the following quadratic: $-x^2+7 x-11$
+
+Please reason step by step, and put your final answer within \\boxed{}."}
 ]
 
 text = tokenizer.apply_chat_template(
@@ -46,7 +55,8 @@ To achieve optimal performance, we recommend the following settings:
 
 1. Enhace the thoughful output：
 
-    a. Make sure the model starts with ```<think>\n``` to prevent generating empty think content. If you use ```apply_chat_template``` and set ```add_generation_prompt=True```, this is automatically implemented, but this may result in replies not having a <think> tag at the beginning, which is normal.
+    a. Make sure the model starts with ```<think>
+``` to prevent generating empty think content. If you use ```apply_chat_template``` and set ```add_generation_prompt=True```, this is automatically implemented, but this may result in replies not having a <think> tag at the beginning, which is normal.
 
     b. Ensure the final input of the model is in the format of ```<｜User｜> [your prompt] <｜Assistant｜><think>```.
 
@@ -56,7 +66,11 @@ To achieve optimal performance, we recommend the following settings:
 
     a. Math questions: Add a statement "```Please reason step by step, and put your final answer within \\boxed{}.```" to the prompt.
 
-    b. Code problems: Add "### Format: Read the inputs from stdin solve the problem and write the answer to stdout. Enclose your code within delimiters as follows.\n \```python\n# YOUR CODE HERE\n\```\n### Answer: (use the provided format with backticks)" to the prompt.
+    b. Code problems: Add "### Format: Read the inputs from stdin solve the problem and write the answer to stdout. Enclose your code within delimiters as follows.
+ \```python
+# YOUR CODE HERE
+\```
+### Answer: (use the provided format with backticks)" to the prompt.
 
 4. In particular, we use ```latex2sympy2``` and ```sympy``` to assist in judging complex Latex formats for the Math500 evaluation script. For all datasets, we generate 64 responses per query to estimate pass@1.
 
@@ -79,5 +93,4 @@ If you find our work helpful, feel free to give us a cite.
   journal={arXiv preprint arXiv:2412.08864},
   year={2024}
 }
-```
-
+```