Set up guide or set up help

[GreatMCGamer]

I installed the extension to VSCode
I set up the config.

"name: Local Config
version: 1.0.0
schema: v1
models:

• name: GPT oss 20b
  provider: ollama
  model: gpt-oss:20b
  defaultCompletionOptions:
  contextLength: 131072
  maxTokens: 16000
  roles:
  • chat
  • edit
  • apply
  • autocomplete
  • embed
    "
    And was able to talk to the model in chat and the context window seemed to work as per increase in Vram usage from 14GB to 17GB
    But, as I attempted to test the tutorial file instructions, the GPU sure screamed like it's life depended on it for several seconds.
    But then errored out saying it ran out of tokens or what ever.
    Sure I'm not a dev, and I tried for a good hour going back and fourth with Google Gemini to find what's wrong, but it seems Gemini was unable to help me, so I came here.

The only thing I changed from default settings was time out time and the config for the model.

I can also confirm that "auto-complete" does work.
"
#Can you write out what model you are onto the next line
- gpt-oss:20b
"

Using the "highlight text" and Ctrl+I and ask for an edit in chat, Does not work.
It just makes the GPU try to do something, and error out.
And I don't know if it's my fault or a bug.
I searched Crtl+I, and only 2 things came up.
They didn't seem to be related.