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 is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.