Skip to content
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.

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

No progress bar in web GUI when downloading layers #89

Open
micouy opened this issue Sep 5, 2023 · 1 comment
Open

No progress bar in web GUI when downloading layers #89

micouy opened this issue Sep 5, 2023 · 1 comment

Comments

@micouy
Copy link

micouy commented Sep 5, 2023

When selecting a new model, the web GUI shows message "loading model" but there's no progress bar. Only in the container's logs I can see that the layers are being downloaded.

Downloading layers.021.ln_m.weight: 100%|██████████| 5.51k/5.51k [00:00<00:00, 2.49MB/s]
Downloading layers.021.ln_m.bias: 100%|██████████| 5.51k/5.51k [00:00<00:00, 2.08MB/s]
-- 33 -- 20230905 10:34:50 WEBUI 172.17.0.1:37680 - "GET /tab-host-have-gpus HTTP/1.1" 200
-- 31 -- 
Downloading layers.021.pw.W1:   0%|          | 0.00/52.4M [00:00<?, ?B/s]
-- 33 -- 20230905 10:34:52 WEBUI 172.17.0.1:37680 - "GET /tab-host-have-gpus HTTP/1.1" 200
Downloading layers.021.pw.W1:  20%|█▉        | 10.5M/52.4M [00:01<00:07, 5.34MB/s]
-- 33 -- 20230905 10:34:54 WEBUI 172.17.0.1:37680 - "GET /tab-host-have-gpus HTTP/1.1" 200
Downloading layers.021.pw.W1:  40%|███▉      | 21.0M/52.4M [00:03<00:05, 6.05MB/s]
Downloading layers.021.pw.W1:  60%|█████▉    | 31.5M/52.4M [00:05<00:03, 6.35MB/s]
-- 33 -- 20230905 10:34:56 WEBUI 172.17.0.1:37680 - "GET /tab-host-have-gpus HTTP/1.1" 200
-- 33 -- 20230905 10:34:58 WEBUI 172.17.0.1:37680 - "GET /tab-host-have-gpus HTTP/1.1" 200
Downloading layers.021.pw.W1:  80%|███████▉  | 41.9M/52.4M [00:06<00:01, 6.20MB/s]
Downloading layers.021.pw.W1: 100%|██████████| 52.4M/52.4M [00:08<00:00, 6.32MB/s]
-- 33 -- 20230905 10:35:00 WEBUI 172.17.0.1:37680 - "GET /tab-host-have-gpus HTTP/1.1" 200

Etc.

Also the model in command is different than selected one which creates confusion as to which model is actually being loaded.

image

@olegklimov
Copy link
Contributor

It's kind of expected, unless we want to hack into the model download process, or parse text output, we don't have a way to forward the progress into the GUI.

But maybe someone could find a cheap and easy way to do it 🤷

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Backlog 🤔
Development

No branches or pull requests

2 participants