-
Notifications
You must be signed in to change notification settings - Fork 8
Conversation
LGTM, do we plan to add something on the daemon side to choose swarm or run it in petals swarm by default? |
We use by default always the public swarm (for now). |
0a3e6de
to
1e4d42e
Compare
1e4d42e
to
a3a7a86
Compare
a3a7a86
to
7265a93
Compare
Sorry about the force-pushes - was debugging this questionable GHA CI behaviour 🤯 |
9ff4ffa
to
beb0765
Compare
80d321d
to
9900bac
Compare
534a4b5
to
0fdf206
Compare
9900bac
to
f095846
Compare
f095846
to
cdc3925
Compare
Are premai-io/CodeLlama-34b-Instruct-hf and petals-team/StableBeluga2 only compatible with Dockerfile:16
> RUN python3 download.py --model $MODEL_ID
Floating point exception (core dumped) Or maybe it's a Petals bug. |
95d23c9
to
9ca7ba1
Compare
TODO: revert when Petals fixes this
9ca7ba1
to
01c62ac
Compare
It's a Petals bug. I will investigate it further. Wanna have the arm images to be done so that I can create a PR to the registry and test the entire flow on Mac :) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm
- did you wanna add falcon-180b first?
- you can link to Added petals models #104 or specifically 01c62ac if reporting to https://github.com/bigscience-workshop/petals/issues/ :)
Falcon requires an HF token in order to fetch the weights due to the terms of services. I am investigating here how to upload the weights to Torrent and then download them with a CLI that we can use inside a dockerfile. :) |
... or just add the HF token to GH repo secrets :) |
Description
Added Petals services
Missing