Open-Assistant
Open-Assistant copied to clipboard
=> ERROR resolve image config for docker.io/docker/dockerfile:1
After % git pull, After % docker login,
/inference % docker compose --profile inference build
[+] Building 0.0s (0/0)
[+] Building 0.1s (1/2)
=> [internal] load build definition from Dockerfile.server 0.0s
[+] Building 0.2s (2/3)
=> [internal] load build definition from Dockerfile.server 0.0s
=> => transferring dockerfile: 39B 0.0s
[+] Building 0.6s (3/3) FINISHED
=> [internal] load build definition from Dockerfile.worker-full 0.0s
=> => transferring dockerfile: 44B 0.0s
[+] Building 0.6s (4/4) FINISHED
=> [internal] load build definition from Dockerfile.server 0.0s
=> => transferring dockerfile: 39B 0.0s
=> [internal] load .dockerignore 0.0s
=> => transferring context: 34B 0.0s
=> ERROR resolve image config for docker.io/docker/dockerfile:1 0.4s
=> [auth] docker/dockerfile:pull token for registry-1.docker.io 0.0s
------
> resolve image config for docker.io/docker/dockerfile:1:
------
failed to solve: rpc error: code = Unknown desc = failed to solve with frontend dockerfile.v0: failed to create LLB definition: no match for platform in manifest sha256:27060abab69e4c749a9bb23b22955123f37be456ccfe76c4bb76f834949a0a97: not found
+1
are you running on mac?
if you’re asking me, yes I use Mac m1 pro
The docker container is not built for arm64, which is why you are getting this error.
Do you have any information on when it might receive support in the near future?
As far as I know, macs don't have nvidia graphics cards, and probably won't be getting any soon, so highly likely that macs won't be supported for GPU inference.
In any case, if you want the model itself, you can get it from hugging face and run it with the transformers library, I think they support cpu on mac.