You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
⚠️ Check for existing issues before proceeding. ⚠️
I have searched the existing issues, and there is no existing issue for my problem
Where are you using SuperAGI?
Linux
Which branch of SuperAGI are you using?
Main
Do you use OpenAI GPT-3.5 or GPT-4?
GPT-3.5
Which area covers your issue best?
Installation and setup
Describe your issue.
I get the following error when trying to run the docker
_compose_gpu.yml script:
Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error mounting "/home/ty/Downloads/.huggingface/download/QwQ-32B-Preview-Q8_0.gguf" to rootfs at "/app/local_model_path": mount src=/home/ty/Downloads/.huggingface/download/QwQ-32B-Preview-Q8_0.gguf, dst=/app/local_model_path, dstFd=/proc/thread-self/fd/8, flags=0x5000: not a directory: unknown: Are you trying to mount a directory onto a file (or vice-versa)? Check if the specified host path exists and is the expected type
I am able to run the normal docker build command but not the GPU one.
I think that I am confused on line 5 and 27 of the docker_compose_gpu.yml. is "/app/local_model_path" verbatim?
That is what I suspect is the issue
How to replicate your Issue?
open Suse tumbleweed updated with nvidia 3090 with nvidea driver & Nvidea-container-toolkit installed.
edit docker_compose_gpu.yml with my path to model + ":/app/local_model_path"
I put this in both of the appropriate places according to this video.
Execute "sudo docker compose -f docker-compose-gpu.yml up --build"
Error
Upload Error Log Content
Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error mounting "/home/ty/Downloads/.huggingface/download/QwQ-32B-Preview-Q8_0.gguf" to rootfs at "/app/local_model_path": mount src=/home/ty/Downloads/.huggingface/download/QwQ-32B-Preview-Q8_0.gguf, dst=/app/local_model_path, dstFd=/proc/thread-self/fd/8, flags=0x5000: not a directory: unknown: Are you trying to mount a directory onto a file (or vice-versa)? Check if the specified host path exists and is the expected type
The text was updated successfully, but these errors were encountered:
Where are you using SuperAGI?
Linux
Which branch of SuperAGI are you using?
Main
Do you use OpenAI GPT-3.5 or GPT-4?
GPT-3.5
Which area covers your issue best?
Installation and setup
Describe your issue.
I get the following error when trying to run the docker
_compose_gpu.yml script:
I am able to run the normal docker build command but not the GPU one.
I think that I am confused on line 5 and 27 of the docker_compose_gpu.yml. is "/app/local_model_path" verbatim?
That is what I suspect is the issue
How to replicate your Issue?
Upload Error Log Content
Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error mounting "/home/ty/Downloads/.huggingface/download/QwQ-32B-Preview-Q8_0.gguf" to rootfs at "/app/local_model_path": mount src=/home/ty/Downloads/.huggingface/download/QwQ-32B-Preview-Q8_0.gguf, dst=/app/local_model_path, dstFd=/proc/thread-self/fd/8, flags=0x5000: not a directory: unknown: Are you trying to mount a directory onto a file (or vice-versa)? Check if the specified host path exists and is the expected type
The text was updated successfully, but these errors were encountered: