HswOAuth/llm_course
19
16
Fork 0
Code Issues 608 Pull Requests Actions Packages Projects Releases Wiki Activity

【求助帖】多模态课程启动 Video-LLaVA 报错 #298

New Issue
Open
opened 2024-10-26 12:36:59 +08:00 by qcwqbc · 3 comments
qcwqbc commented 2024-10-26 12:36:59 +08:00
Copy Link

出现
(videollava) root@autodl-container-7b7a41b559-cdd3bc5f:~/autodl-tmp/Video-LLaVA# python -m videollava.serve.gradio_web_server
[2024-10-26 12:28:03,631] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect)
/root/miniconda3/envs/videollava/lib/python3.10/site-packages/torchvision/transforms/_functional_video.py:6: UserWarning: The 'torchvision.transforms._functional_video' module is deprecated since 0.12 and will be removed in the future. Please use the 'torchvision.transforms.functional' module instead.
warnings.warn(
/root/miniconda3/envs/videollava/lib/python3.10/site-packages/torchvision/transforms/_transforms_video.py:22: UserWarning: The 'torchvision.transforms._transforms_video' module is deprecated since 0.12 and will be removed in the future. Please use the 'torchvision.transforms' module instead.
warnings.warn(
/root/miniconda3/envs/videollava/lib/python3.10/site-packages/torchvision/transforms/functional_tensor.py:5: UserWarning: The torchvision.transforms.functional_tensor module is deprecated in 0.15 and will be removed in 0.17. Please don't rely on it. You probably just need to use APIs in torchvision.transforms.functional or in torchvision.transforms.v2.functional.
warnings.warn(
You are using a model of type video_llava to instantiate a model of type llava. This is not supported for all configurations of models and can yield errors.
上面这些错误
跟我替换了这条pip install flash-attn --no-build-isolation命令有关系吗？
主要是一直卡着不动我就手动下了个
flash_attn-2.6.3+cu118torch2.0cxx11abiFALSE-cp310-cp310-linux_x86_64.whl

第一次是能正常运行的，然后重启就不行了。
怎么解决

出现 (videollava) root@autodl-container-7b7a41b559-cdd3bc5f:~/autodl-tmp/Video-LLaVA# python -m videollava.serve.gradio_web_server [2024-10-26 12:28:03,631] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) /root/miniconda3/envs/videollava/lib/python3.10/site-packages/torchvision/transforms/_functional_video.py:6: UserWarning: The 'torchvision.transforms._functional_video' module is deprecated since 0.12 and will be removed in the future. Please use the 'torchvision.transforms.functional' module instead. warnings.warn( /root/miniconda3/envs/videollava/lib/python3.10/site-packages/torchvision/transforms/_transforms_video.py:22: UserWarning: The 'torchvision.transforms._transforms_video' module is deprecated since 0.12 and will be removed in the future. Please use the 'torchvision.transforms' module instead. warnings.warn( /root/miniconda3/envs/videollava/lib/python3.10/site-packages/torchvision/transforms/functional_tensor.py:5: UserWarning: The torchvision.transforms.functional_tensor module is deprecated in 0.15 and will be **removed in 0.17**. Please don't rely on it. You probably just need to use APIs in torchvision.transforms.functional or in torchvision.transforms.v2.functional. warnings.warn( You are using a model of type video_llava to instantiate a model of type llava. This is not supported for all configurations of models and can yield errors. 上面这些错误 跟我替换了这条pip install flash-attn --no-build-isolation命令有关系吗？ 主要是一直卡着不动我就手动下了个 flash_attn-2.6.3+cu118torch2.0cxx11abiFALSE-cp310-cp310-linux_x86_64.whl 第一次是能正常运行的，然后重启就不行了。 怎么解决
1729917055703.jpg
127 KiB
1729917277848.jpg
41 KiB
1729912716265.jpg
352 KiB
1729917055703.jpg 1729917277848.jpg 1729912716265.jpg
12019701659cs commented 2024-10-28 14:05:30 +08:00
Copy Link
  1. 遇到waring可以不用管，warning是建议，不会影响运行。
  2. 没有到gradio运行阶段，检查下gradio的配置，包括：临时设置huggingface镜像，gradio公网share的设置。
  3. 不用手动下flash_attn，会有额外不可预料的问题。
1. 遇到waring可以不用管，warning是建议，不会影响运行。 2. 没有到gradio运行阶段，检查下gradio的配置，包括：临时设置huggingface镜像，gradio公网share的设置。 3. 不用手动下flash_attn，会有额外不可预料的问题。
rebibabo commented 2024-10-28 21:46:51 +08:00
Copy Link

运行到这里卡了，tokenizer可以加载，到模型就卡住了
image
不过运行下面代码
image
差不多1分钟左右加载成功了
image
多等几分钟，就可以加载了，但是最终显示错误
image
打开下面的文件，添加两段代码就可以成功运行了
image
后面下载了那些文件还是不能共享url，报下面错误
image-20241028230120381
还是老老实实开通到吧》。。
后面测试样例又报错，看来前面config不能那么改
image

运行到这里卡了，tokenizer可以加载，到模型就卡住了 ![image](/attachments/e8d97c29-4088-426a-bebc-35dcdcc65c14) 不过运行下面代码 ![image](/attachments/c9703158-6b1e-4f43-80a1-2cbd7e8351b4) 差不多1分钟左右加载成功了 ![image](/attachments/e87e0364-7f5a-496b-ab49-16cf105d7fcf) 多等几分钟，就可以加载了，但是最终显示错误 ![image](/attachments/fda68f36-57b3-42e5-9c39-53e407f64011) 打开下面的文件，添加两段代码就可以成功运行了 ![image](/attachments/4ba655a0-e042-44ff-994e-1b27363cdabb) 后面下载了那些文件还是不能共享url，报下面错误 ![image-20241028230120381](/attachments/8df760dc-56aa-4d8e-9e03-c636ec3c9e35) 还是老老实实开通到吧》。。 后面测试样例又报错，看来前面config不能那么改 ![image](/attachments/6c977ef2-965c-4099-8de1-982f3efeba06)
image.png
163 KiB
image.png
19 KiB
image.png
43 KiB
image.png
70 KiB
image.png
272 KiB
image-20241028230120381.png
10 KiB
image.png
92 KiB
sunnyday commented 2024-11-01 16:12:08 +08:00
Copy Link

@rebibabo 这个问题解决了吗
image

@rebibabo 这个问题解决了吗 ![image](/attachments/94af83a7-8e1d-4d9b-ac6b-f09c0e49a6c0)
image.png
30 KiB
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels   
bug

Something is not working

  
duplicate

This issue or pull request already exists

  
enhancement

New feature

  
help wanted

Need some help

  
invalid

Something is wrong

  
question

More information is needed

  
wontfix

This won't be fixed

No Label
bug
duplicate
enhancement
help wanted
invalid
question
wontfix
Milestone
Clear milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
No Assignees
4 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: HswOAuth/llm_course#298
No description provided.
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?