Commit History
-
Add Qwen DevOps Foundation LoRA adapter - 4xL40S trained
Verified signature- Fine-tuned Qwen3-8B on DevOps datasets using LoRA - Trained on 4x NVIDIA L40S GPUs for ~3 hours - Supports Docker, Kubernetes, CI/CD, and SRE tasks - 174MB LoRA adapter + tokenizer files - Ready for inference with base Qwen/Qwen3-8B modela6d0d22