初始化项目，由ModelHub XC社区提供模型

Model: QuantFactory/SmallThinker-3B-Preview-GGUF Source: Original Platform
2026-10-14 06:26:14 +08:00
commit bf4eee2091
17 changed files with 170 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,78 @@
+
+---
+
+datasets:
+- PowerInfer/QWQ-LONGCOT-500K
+- PowerInfer/LONGCOT-Refine-500K
+base_model:
+- Qwen/Qwen2.5-3B-Instruct
+
+---
+
+[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
+
+
+# QuantFactory/SmallThinker-3B-Preview-GGUF
+This is quantized version of [PowerInfer/SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview) created using llama.cpp
+
+# Original Model Card
+
+# SmallThinker-3B-preview
+
+We introduce **SmallThinker-3B-preview**, a new model fine-tuned from the [Qwen2.5-3b-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) model. 
+
+## Benchmark Performance
+
+| Model | AIME24 | AMC23 | GAOKAO2024_I | GAOKAO2024_II | MMLU_STEM | AMPS_Hard | math_comp |
+|---------|--------|-------|--------------|---------------|-----------|-----------|-----------|
+| Qwen2.5-3B-Instruct | 6.67 | 45 | 50 | 35.8 | 59.8 | - | - |
+| SmallThinker | 16.667 | 57.5 | 64.2 | 57.1 | 68.2 | 70 | 46.8 |
+| GPT-4o | 9.3 | - | - | - | 64.2 | 57 | 50 |
+
+Limitation: Due to SmallThinker's current limitations in instruction following, for math_comp we adopt a more lenient evaluation method where only correct answers are required, without constraining responses to follow the specified AAAAA format.
+
+
+## Intended Use Cases
+
+SmallThinker is designed for the following use cases:
+
+1.  **Edge Deployment:** Its small size makes it ideal for deployment on resource-constrained devices.
+2.  **Draft Model for QwQ-32B-Preview:** SmallThinker can serve as a fast and efficient draft model for the larger QwQ-32B-Preview model. From my test, in llama.cpp we can get 70% speedup (from 40 tokens/s to 70 tokens/s).
+
+## Training Details
+
+The model was trained using 8 H100 GPUs with a global batch size of 16. The specific configuration is as follows:
+
+```
+neat_packing: true
+cutoff_len: 16384
+per_device_train_batch_size: 2
+gradient_accumulation_steps: 1
+learning_rate: 1.0e-5
+num_train_epochs: 3
+lr_scheduler_type: cosine
+warmup_ratio: 0.02
+bf16: true
+ddp_timeout: 180000000
+weight_decay: 0.0
+```
+
+The SFT (Supervised Fine-Tuning) process was conducted in two phases:
+
+1. First Phase:
+   - Used only the PowerInfer/QWQ-LONGCOT-500K dataset
+   - Trained for 1.5 epochs
+
+2. Second Phase:
+   - Combined training with PowerInfer/QWQ-LONGCOT-500K and PowerInfer/LONGCOT-Refine datasets
+   - Continued training for an additional 2 epochs
+
+
+## Limitations & Disclaimer
+
+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.
+*   **Limited Knowledge:** Due to limited SFT data and the model's relatively small scale, its reasoning capabilities are constrained by its knowledge base.
+*   **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.