VSCODE + Cline + Ollama + Qwen2.5-Coder-32B-Instruct.Q8_0
Although in general the setup works smoothly, but I am running into an issue that appears to be specifically model related.
As a file is edited, Qwen deletes working sections of code that it has NO business deleting. I did not ask for anything that would require such deletions.
For example, I asked the code to be modified so that the page or a list element be refreshed after a form submission. The model then deleted the handlers for a "delete" and "view" file buttons, making them inactive.
Is there anything I can put in the prompt to prevent code deletions that were not requested?
Thanks.
Hello @BigDeeper , I think you would need to set ollama max context length to higher (at least 8k imo if the repo is small, 16k and above if it is a huge repo). This happened to me before.
Hello @BigDeeper , I think you would need to set ollama max context length to higher (at least 8k imo if the repo is small, 16k and above if it is a huge repo). This happened to me before.
My context size is 19456. It is a trade off between being able to put all 65 layers on GPUs, versus the context size. It is NOT simply truncating files, it just fails to copy existing code sections into new versions.
Maybe it is possible to modify the prompt to help the model deal with this, but nothing obvious comes to mind.
All my files are pretty small, 450 lines are the largest. Most are fewer than 200 lines.