Adds support for Octocoder for autocomplete#930
Conversation
|
nice catch, thanks for the fix! I haven't tried octocoder yet, lmk how it goes : ) |
|
Hi @ajalexander, yesterday we shared some updates with our contributors about how we're aiming to improve the contribution process. Part of this included the addition of a Contributor License Agreement (CLA) to protect both contributors and the project. We're reaching out to ask that previous contributors sign it. Could you please take a moment to sign, or if you have any questions send me a message? (either here or nate@continue.dev would work) To do so, you just need to post a comment below with the following text: ❤️ Thank you for the work you've done on Continue, and let me know if you have any suggestions on how we can make the project even better! |
|
I have read the CLA Document and I hereby sign the CLA You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot. |
This change adds support for Octocoder similar to the change for StarChat made in #847.
Current Issue
Similar to the issue fixed in #847, the model I'm working with is TheBloke/Octocoder-GPTQ. The "GPT" in that name is currently causing the extension to use the GPT template.
The change
By adding
octocoderas one of the search strings alongside thestarcodermodels, the template code will now return thestableCodeFirmTemplaterather than thegptAutocompleteTemplate.Testing
Prior to the change, the extension output would contain:
After the change, the extension output contains: