aloobun/d-Qwen1.5-0.5B is a 0.6 billion parameter student model based on the Qwen1.5 architecture, distilled from a larger Qwen1.5-1.8B teacher model. It demonstrates improved performance over its base model on specific benchmarks, notably TruthfulQA and GSM8K. This model is optimized for tasks requiring factual accuracy and mathematical reasoning, making it suitable for resource-constrained environments.
No reviews yet. Be the first to review!
Hugging Face