This website uses Cookies. Click Accept to agree to our website's cookie use as described in our Privacy Policy. Click Preferences to customize your cookie settings.
Hi,I'm trying to get a Cloud Workstation instantiated with at least
128GB of RAM, but preferably 256GB or more for some specialized
development and testing. I'd like to use Cloud Workstation because I use
IntelliJ and that works well with it.However,...
Creating a Vertex AI Workbench instance works without a problem.
However, I wanted to follow a tutorial to connect to an instance from a
local IDE, and for that I need to create a Vertex AI Workbench instance
that doesn't have an external IP.When I u...
I've managed to deploy Mistral-7B-v0.1 to a Vertex AI endpoint. For this
I've used its model id in the Model Garden
("mistralai/Mistral-7B-v0.1"). But when I use this id for other things,
it doesn't work, for example:from vertexai.language_models imp...
I'm using the prompt template directly from Mistral: { "instances": [ {
"prompt": "<S>[INST] What is your favourite colour and why? [/INST]My
favorite color is blue.</S>[INST] And which one after that? [/INST]" }
], "parameters": { "max_tokens": -1 } } Then...
Support has helped me resolve this. Even though there is no mention of
this in the documentation that I could find, Private Google Access needs
to be turned on for the zone you're instantiating a Workbench Instance
with External IP disabled.This can ...
As a follow-up, I never fixed this. I just started deploying Mistral-7B
and Mixtral-8x7B with vLLM using the OpenAI-compatible API and that has
resolved it for me. But it's obviously just a workaround.
Thanks, I tried many different variants of the string, removing the
prefix, removing the version, appending @001, making everything lower
case, etc. Nothing seems to work.However, it seems to me that the model
garden instance only has the Google stuf...
