使用Qwen2.5-14B-scipy为底，数据使用lima-erp的LoRA。 训练结果是一直都没有收敛，Loss总是在2.5~2.3之前，是个失败的产物。
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.