Issues
- 1
- 1
- 0
请问是否可以在LMDeploy、vLLM等部署框架上使用?
#43 opened by Shubao-Zhao - 1
Issue about the visual case provided in the paper
#41 opened by Adherer - 6
您好,请问utils.py里面以下代码都为None,是什么导致的
#42 opened by zhly0 - 6
Issue about visualization
#40 opened by Melon-Xu - 1
- 3
Can not reproduce the results on LLaVA-1.5
#39 opened by wangyouze - 2
CUDA error: out of memory
#36 opened by Melon-Xu - 2
Random 500 samples in MSCOCO
#37 opened by Adherer - 4
Random 500 samples in MSCOCO?
#12 opened by zhaoshitian - 4
可视化问题
#34 opened by OliverLeeXZ - 1
- 2
CHAIR hallucination evaluation
#30 opened by running-alpaca - 2
- 14
关于复现POPE的结果问题
#33 opened by 1906200111 - 6
CHAIR Reproduction Bugs
#20 opened by xing0047 - 4
GPU information
#21 opened by KlaineWei - 2
关于是否是幻觉句子的问题
#31 opened by clclclaiggg - 2
是否能支持4.37.2 的transformers
#16 opened by awzhgw - 1
Does the method to find `knowledge aggregation pattern` have any relevant papers to reference in NLP domain?
#26 opened by shanpoyang654 - 3
Truncation of generated results
#27 opened by lalulxm - 2
- 0
Shikra Version
#29 opened by summoneryhl - 1
stopping criteria
#25 opened by yeonju7kim - 1
运行vis.ipynb报错
#23 opened by Ivesfu - 1
Questions about Figure 3 in paper
#18 opened by minhoooo1 - 1
Over-Trust Logit Penalty
#17 opened by hubujy - 1
AssertionError: OPERA does not support beam=1 in the current version. It will be added in the future.
#15 opened by FanshuoZeng - 9
- 0
reproducing shikra problem
#22 opened by KlaineWei - 2
reproducing the result
#19 opened by JEONG8652 - 1
- 10
- 1
Attention map plotting
#10 opened by franciscoliu - 1
Acknowledge LAVIS
#11 opened by dxli94 - 1
- 1
Does it work well on videos?
#1 opened by YajieW99 - 4
Reproducing MiniGPT-4's POPE result
#8 opened by Ocean-627 - 1
opera_greedy_search implemented ?
#6 opened by BillChan226 - 2
Model inference speed is slow
#3 opened by hlz0606 - 2
- 0
- 1