Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+results.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,87 @@
 ---
-license: mit
-language:
-- en
-metrics:
-- code_eval
+license: apache-2.0
 base_model:
-- Qwen/Qwen3-8B-Base
-pipeline_tag: text-generation
+  - Qwen/Qwen3-8B-Base
+datasets:
+  - IIGroup/X-Coder-SFT-376k
+language:
+  - en
 tags:
-- code
-- competitive programming
----
+  - code
+  - sft
+  - competitive-programming
+---
+
+# X-Coder-SFT-Qwen3-8B
+
+X-Coder-SFT-Qwen3-8B is a code generation model fine-tuned on fully synthetic instruction data, designed for competitive programming tasks. It serves as the foundation for subsequent RLVR training.
+
+## Model Description
+
+- **Base Model**: [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base)
+- **Training Method**: Supervised Fine-Tuning (SFT)
+- **Training Data**: [IIGroup/X-Coder-SFT-376k](https://huggingface.co/datasets/IIGroup/X-Coder-SFT-376k) (376k fully synthetic samples)
+- **Parameters**: 8B
+
+## Training
+
+This model was trained using [ms-swift](https://github.com/modelscope/ms-swift). For training details and code, please refer to the [X-Coder GitHub repository](https://github.com/JieWu02/X-Coder).
+
+## Performance
+
+![Results](results.png)
+
+**Performance on LiveCodeBench v5.** X-Coder-SFT demonstrates strong coding capabilities trained entirely on synthetic data.
+
+## Recommended Inference Parameters
+
+| Parameter | Value |
+|-----------|-------|
+| temperature | 0.6 |
+| top_p | 0.95 |
+| top_k | 20 (or -1 to disable) |
+| max_new_tokens | 32768 |
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "IIGroup/X-Coder-SFT-Qwen3-8B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+
+prompt = "Write a Python function to solve the two sum problem."
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=32768,
+    temperature=0.6,
+    top_p=0.95,
+    top_k=20,
+    do_sample=True
+)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Related Models
+
+- **RL Model**: [IIGroup/X-Coder-RL-Qwen3-8B](https://huggingface.co/IIGroup/X-Coder-RL-Qwen3-8B) - RLVR trained version achieving 64.0 on LiveCodeBench
+
+## Citation
+
+```bibtex
+@inproceedings{
+anonymous2025xcoder,
+title={X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests},
+author={Anonymous},
+booktitle={Submitted to The Fourteenth International Conference on Learning Representations},
+year={2025},
+url={https://openreview.net/forum?id=jp4dzBilqH},
+note={under review}
+}
+```
+
+## License
+
+This project is licensed under the Apache License 2.0.