SmallThinker-3B-preview

Benchmark Performance

Intended 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

1. First Phase:
   • Used only the PowerInfer/QWQ-LONGCOT-500K dataset
   • Trained for 1.5 epochs

### model
model_name_or_path: /home/syx/Qwen2.5-3B-Instruct

### method
stage: sft
do_train: true
finetuning_type: full
deepspeed: examples/deepspeed/ds_z3_config.json

### dataset
dataset: o1-v2
template: qwen
neat_packing: true
cutoff_len: 16384
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: saves/qwen2-01-qat/full/sft
logging_steps: 1
save_steps: 1000
plot_loss: true
overwrite_output_dir: true

1. Second Phase:
   • Combined training with PowerInfer/QWQ-LONGCOT-500K and PowerInfer/LONGCOT-Refine datasets
   • Continued training for 2 additional epochs

### model
model_name_or_path: saves/qwen2-01-qat/full/sft/checkpoint-24000

### method
stage: sft
do_train: true
finetuning_type: full
deepspeed: examples/deepspeed/ds_z3_config.json

### dataset
dataset: o1-v2, o1-v3
template: qwen
neat_packing: true
cutoff_len: 16384
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: saves/qwen2-01-qat/full/sft
logging_steps: 1
save_steps: 1000
plot_loss: true
overwrite_output_dir: true

Limitations & Disclaimer

• 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.