Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,41 @@
+---
+license: apple-amlr
+base_model:
+- Qwen/Qwen3-4B
+tags:
+- self-distillation
+- code-generation
+- ssd
+library_name: transformers
+---
+
+# SSD-Qwen3-4B-Thinking
+
+This model was produced using **Simple Self-Distillation (SSD)**, a method that improves code generation by fine-tuning a language model on its own sampled outputs—without rewards, verifiers, teacher models, or reinforcement learning.
+
+- **Base model:** [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B)
+- **Variant:** thinking
+- **Self-distillation sampling:** temperature=0.7, top_p=0.95, top_k=20
+
+## Method
+
+SSD samples solutions from the base model using non-unit temperature and top-k/top-p truncation, then fine-tunes on those samples via standard supervised learning. Despite its simplicity, SSD yields large gains on competitive programming benchmarks, with improvements concentrating on harder problems. The mechanism traces to resolving a *precision–exploration conflict*: SSD reshapes token distributions in a context-dependent way so that a single global decoding configuration becomes far more effective at evaluation time.
+
+## Paper
+
+**Embarrassingly Simple Self-Distillation Improves Code Generation**
+
+Ruixiang Zhang, Richard He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("apple/SSD-Qwen3-4B-Thinking")
+tokenizer = AutoTokenizer.from_pretrained("apple/SSD-Qwen3-4B-Thinking")
+```
+
+## License
+
+This model is released under the [Apple Sample Code License](https://huggingface.co/apple/CLaRa-7B-Instruct/blob/main/LICENSE).