HYHe

model--llama2-7b-chat, meet the same problem

``` from mmdet.apis import init_detector, inference_detector, DetInferencer from mmdet.registry import VISUALIZERS import cv2, sys, pickle import mmcv from rich.pretty import pprint config_file = r'/Region-proposal/mmdetection/faster-rcnn_r101_fpn_2x_coco.py' checkpoint_file = r'/Region-proposal/mmdetection/faster_rcnn_r101_fpn_2x_coco_bbox_mAP-0.398_20200504_210455-1d2dac9c.pth' img = 'sample/sample.png'...

https://github.com/vllm-project/vllm/pull/20750 This issue should have been resolved, but due to server issues, I am unable to upgrade vllm to a higher version to prevent conflicts with many Python libraries. How...

@noooop @ignorejjj thanks!

Hello, after loading the model weights with LoRA, I encountered the same issue where the model outputs were blank. Have you found a solution? Thank you.