update model card and license

README.md

@@ -11,7 +11,7 @@ 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.
+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 using standard supervised learning.
 
 - **Base model:** [Qwen/Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507)
 - **Variant:** thinking
@@ -46,6 +46,10 @@ model = AutoModelForCausalLM.from_pretrained("apple/SSD-Qwen3-4B-Thinking")
 tokenizer = AutoTokenizer.from_pretrained("apple/SSD-Qwen3-4B-Thinking")
 ```
 
+## Intended Use
+
+Research on code generation and self-distillation methods.
+
 ## License
 
 This model is released under the [Apple Machine Learning Research Model License](https://huggingface.co/apple/SSD-Qwen3-4B-Thinking/blob/main/LICENSE).