minor

README.md

@@ -1,17 +1,17 @@
 ---
 {}
 ---
-# Introducing SmallThinker-3B: A Lightweight Model Fine-tuned on QwQ Synthetic Data
+# Introducing SmallThinker-3B-alpha: A Small Model Fine-tuned on QwQ Synthetic Data
 
-We introduce **SmallThinker-3B**, a new model fine-tuned from the [Qwen2.5-3b-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) model using synthetic data generated by [QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview). 
+We introduce **SmallThinker-3B-alpha**, a new model fine-tuned from the [Qwen2.5-3b-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) model using synthetic data generated by [QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview). 
 
 ## Benchmark Performance
 
-| Model | AMPS_Hard Score |
-|---------|----------------|
-| SmallThinker | 58.0 |
-| GPT-4o (2024-08-06) | 54.0 |
-| Qwen2.5-3B-Instruct | 44.0 |
+| Model | AIME24 | AMC23 | GAOKAO2024_I | GAOKAO2024_II | MMLU_STEM | AMPS_Hard | math_comp |
+|---------|--------|-------|--------------|---------------|-----------|-----------|-----------|
+| Qwen2.5-3B-Instruct | 6.67 | 45 | 50 | 35.8 | - | - | - |
+| SmallThinker | 16.667 | 57.5 | 64.2 | 57.1 | 68.2 | 70 | 46.8 |
+| GPT-4o | 9.3 | - | - | - | 64.2 | 57 | 50 |
 
 
 
@@ -27,4 +27,5 @@ SmallThinker is designed for the following use cases:
 Please be aware of the following limitations:
 
 *   **Language Limitation:** The model has only been trained on English-language datasets, hence its capabilities in other languages are still lacking.
-*   **Unpredictable Outputs:** The model may produce unexpected outputs due to its size and probabilistic generation paradigm. Users should exercise caution and validate the model's responses.
+*   **Unpredictable Outputs:** The model may produce unexpected outputs due to its size and probabilistic generation paradigm. Users should exercise caution and validate the model's responses.
+*   **Repetition Issue:** The model tends to repeat itself when answering high-difficulty questions. Please increase the `repetition_penalty` to mitigate this issue.