Qwen2 Model Fine-tuning & Deployment

8 repos

Fine-tuned variants and deployment configurations of Alibaba's Qwen2 language models across multiple scales (1.5B to 72B parameters), optimized for conversational and text-generation tasks. Repositories showcase supervised fine-tuning (SFT), direct preference optimization (DPO), and full model adaptation techniques, with a focus on maintaining OpenAI-compatible endpoints for inference and integration.

Related clusters