Skip to content

Issues: open-compass/VLMEvalKit

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

65 Open 192 Closed
65 Open 192 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Llama-3.2-11B-Vision-Instruct来测评MMStar和HallusionBench
#685 opened Dec 23, 2024 by wangchunhui06
WildVision raises exception
#684 opened Dec 23, 2024 by YuanLiuuuuuu
ChartQA/DocVQA 分数异常
#683 opened Dec 23, 2024 by OrlandoBloom16
关于 RealWorldQA 以及 MMMU_DEV_VAL 里面部分条目的问题
#677 opened Dec 19, 2024 by lihytotoro
2
MME-realworld benchmark如何设置local path？
#676 opened Dec 19, 2024 by ZihaoZheng98
1
AUTO_SPLIT=1 如何搭配CUDA_VISIBLE_DEVICES=使用
#674 opened Dec 19, 2024 by ZihaoZheng98
有InternVL 2.5和deepseek vl2的支持计划么
#673 opened Dec 18, 2024 by JohnTang93
4
awq model eval support request Feature Request Extra attention is needed
#671 opened Dec 17, 2024 by sanbuphy
@kennymckormick
local judge model not work, meet error when model.working()
#670 opened Dec 16, 2024 by ylsaker
1
OlympiadBench数量跟论文不一致
#667 opened Dec 14, 2024 by wdp-007
1
The image quality in VLMEvalKit is compressed and lower than that provided by Benchmark itself.
#665 opened Dec 13, 2024 by Sync-yxh
1
Local judge LLM?
#664 opened Dec 12, 2024 by lyzhongcrd
2
与榜单指标差距过大，MTVQA和MME
#663 opened Dec 12, 2024 by GoogleAlphaZero
@FangXinyu-0913
4
报错
#661 opened Dec 12, 2024 by 0704highlight
1
测评MMVET，用llama3.2-11b-vision时，openai的密钥为空，会报错
#654 opened Dec 6, 2024 by GoogleAlphaZero
2
The locally saved glm-4v-9b model encounters errors during evaluation, which are related to the way the tokenizer is loaded
#653 opened Dec 6, 2024 by WeiweiZhang1
1
MathVerse_MINI 指向的 DATASET_URL 失效
#652 opened Dec 5, 2024 by lihytotoro
2
AutoScoringJudge文件
#651 opened Dec 5, 2024 by wksuixin
您好，能否增加一些中文的评估benchmark啊？比如CMMMU，支持的中文benchmark太少了
#650 opened Dec 5, 2024 by GoogleAlphaZero
Not able to reproduce InternVL-8b x Blink result
#649 opened Dec 5, 2024 by David-BominWei
5
llama3.2_11b_vision用MathVista_MINI测评时，由于不设置.env文件，会报错
#646 opened Dec 4, 2024 by GoogleAlphaZero
3
LLAVA-one-vision MMMU 性能评测差别很大
#645 opened Dec 4, 2024 by linxid
1
用Chartqa测评LLama3.2-11b-vision时，结果全部为0
#644 opened Dec 4, 2024 by GoogleAlphaZero
1
Does VLMEvalKit support Paged Attention evaluation?
#641 opened Dec 2, 2024 by weiaicunzai
Discrepancy in MM Math Evaluation Results: Possible Issue with Answer Extraction in VLMEvalkit
#638 opened Dec 1, 2024 by mantle2048
6
ProTip! Add no:assignee to see everything that’s not assigned.