Skip to content

Issues: QwenLM/Qwen2.5-VL

Beta
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

704 Open 260 Closed
704 Open 260 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

Can the model be fine-tuned using video-type Inputs(multi image)?
#1164 opened Apr 29, 2025 by LEE-JAEHA
Division of the RefCOCO dataset
#1163 opened Apr 29, 2025 by zhangjinrong731
demo script for chain-of-thought
#1162 opened Apr 28, 2025 by garychan22
A question for finetune qwen2.5 in my custom grounding dataset
#1161 opened Apr 28, 2025 by Chengnotwang
6
vllm 怎样在启动时设置可处理图像的尺寸？
#1160 opened Apr 28, 2025 by jyC23333
官方推理示例代码对不同的尺寸图片结果差异大
#1159 opened Apr 28, 2025 by glunce
V100推理3B模型OOM
#1157 opened Apr 27, 2025 by dyhdesu
4
视频抽帧策略
#1156 opened Apr 27, 2025 by HaoYin116
2
android control复现细节
#1155 opened Apr 26, 2025 by flashcp
2
qwen2.5vl训练推理prompt一致性问题
#1154 opened Apr 25, 2025 by Ziyu-Jin
1
low accelerator utilization during training
#1153 opened Apr 25, 2025 by windprak
Qwen2.5-VL process_vision_info是否有加速的方法
#1152 opened Apr 25, 2025 by Karna-Horizon
2
使用vllm部署Qwen2.5-VL-7B-Instruct，发送请求时是否需要对图片数据做预处理？
#1151 opened Apr 25, 2025 by lydyc
5
Cuda out of memory on 8*80GB H100 Machine - qwen2.5-vl-32-instruct finetune
#1150 opened Apr 25, 2025 by Dineshkumar-Anandan-ZS0367
关于Qwen2.5-VL-72B输出长度不足的问题
#1147 opened Apr 24, 2025 by Xieyyyy
1
grad_norm always zero when finetuning with attn_implementation="sdpa" or attn_implementation="eager"
#1146 opened Apr 23, 2025 by NebulaKoder
1
访问predic接口异常
#1144 opened Apr 23, 2025 by cxkjnszstm
损失骤降，推理报错inf, nan or element ＜ 0
#1143 opened Apr 23, 2025 by xxxwww337
1
Qwen2.5-VL关于ocr识别被涂改文字的识别
#1142 opened Apr 23, 2025 by zhangdi-520
1
请问目前此repo支持对Qwen2.5VL进行继续预训练吗
#1141 opened Apr 23, 2025 by XCF-Mike
Max sequence length in data_flatten mode
#1140 opened Apr 22, 2025 by QuiPyJu
500 Internal Server Error asyncio.exceptions.TimeoutError
#1139 opened Apr 22, 2025 by Marydsy
suspected bugs in the finetune code
#1138 opened Apr 22, 2025 by 0001Henry
Qwen2.5-VL Grounding Example for multiple bbox
#1137 opened Apr 22, 2025 by RushDon
qwen2.5vl在视频推理时，如何合理设置max_pixels、min_pixels以及fps的值？
#1136 opened Apr 22, 2025 by Wangqi12138
1
ProTip! Add no:assignee to see everything that’s not assigned.