deepseek-distill-qwen
PublicThe Deepseek Distillation of Qwen project fine-tunes the Qwen model using Deepseek, optimizing both performance and inference speed through a series of scripts for question generation, model fine-tuning, and evaluation.
The Deepseek Distillation of Qwen project fine-tunes the Qwen model using Deepseek, optimizing both performance and inference speed through a series of scripts for question generation, model fine-tuning, and evaluation.