search

dvlab-research / LongLoRA

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
http://arxiv.org/abs/2309.12307
Apache License 2.0
2.62k stars 274 forks source link

模型完全没法正常输出 #187

Closed Tangent-90C closed 5 months ago

Tangent-90C commented 5 months ago

我连续试了3个LongLoRA微调出的模型

这3个模型都没法正常输出（直接返回空结果 或 大段重复胡言乱语），不论是用transformers框架推理，还是运行该repo的demo.py都没法work。

image

image

Tangent-90C commented 5 months ago

把环境重装之后就解决了