Update README.md

README.md

@@ -9,6 +9,9 @@ base_model:
 - infly/OpenCoder-8B-Base
 pipeline_tag: text-generation
 library_name: transformers
+datasets:
+- OpenCoder-LLM/opencoder-sft-stage1
+- OpenCoder-LLM/opencoder-sft-stage2
 ---
 
 
@@ -43,7 +46,16 @@ library_name: transformers
 | OpenCoder-1.5B-Instruct  |      4K       | 🤗 [HuggingFace](https://huggingface.co/infly/OpenCoder-1.5B-Instruct) |
 | OpenCoder-8B-Instruct  |      8K       | 🤗 [HuggingFace](https://huggingface.co/infly/OpenCoder-8B-Instruct) |
 
-## 3. Benchmarks
+
+## 3. Datasets
+
+|         Dataset       | Num |                                Download                                 |
+|:---------------------:|:---------------:|:-----------------------------------------------------------------------:|
+| OpenCoder-SFT-Stage1  |      4.21 M       | 🤗 [HuggingFace](https://huggingface.co/datasets/OpenCoder-LLM/opencoder-sft-stage1)  |
+| OpenCoder-SFT-Stage2  |      375 K      | 🤗 [HuggingFace](https://huggingface.co/datasets/OpenCoder-LLM/opencoder-sft-stage2)  |
+
+
+## 4. Benchmarks
 
 **Note:** For the detailed evaluation results, please refer to [our paper](https://arxiv.org/pdf/2411.04905).
 
@@ -67,7 +79,7 @@ library_name: transformers
 | MultiPL-E (AVG) |     57.5     |     71.0     |
 
 
-## 4. Inference
+## 5. Inference
 
 ### Inference with Huggingface's Transformers
 
@@ -96,11 +108,11 @@ print(result)
 
 <!-- ### Inference with vLLM (recommended) -->
 
-## 5. License
+## 6. License
 
 OpenCoder series (including Base and Chat) support commercial applications under a permissive [License](https://huggingface.co/infly/OpenCoder-8B-Instruct/blob/main/LICENSE).
 
-## 6. Citation
+## 7. Citation
 ```
 @inproceedings{Huang2024OpenCoderTO,
   title={OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models},