how to download the load the model

[jimleee]

i am trying to install with docker, i am now in this step：“llama-gpt-llama-gpt-ui-1 | [INFO wait] Host [llama-gpt-api-13b:8000] not yet available..”， now my question is how to download the load the model? below is the guideline.

Note: On the first run, it may take a while for the model to be downloaded to the /models directory. You may see lots of output like for a few minutes, which is normal:

llama-gpt-llama-gpt-ui-1 | [INFO wait] Host [llama-gpt-api-13b:8000] not yet available... After the model has been downloaded and loaded, and the API server is running, you'll see an output like:

llama-gpt-llama-gpt-api-13b-1 | INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

[debarko]

How long does it take to download? What connection speeds to you have?

[arch1v1st]

@jimlee - it happens automatically upon starting the docker container and totally depends on your internet download speeds. See this for a sense of the size:

https://github.com/getumbrel/llama-gpt#supported-models

On Windows, I used the Task Manager > Performance tab to monitor the speed and completion. It will then take a while to start up afterwards. Note - if you happen to interrupt this while the download is underway, you may need to delete the model from /models/ and restart the containers to retry.