Completion options are ignored for tab autocomplete model
Before submitting your bug report
- [ ] I believe this is a bug. I'll try to join the Continue Discord for questions
- [ ] I'm not able to find an open issue that reports the same bug
- [ ] I've seen the troubleshooting guide on the Continue Docs
Relevant environment info
- OS: Linux
- Continue version:1.0.19
- IDE version:
- Model: Qwen-7b-coder-base
- config:
name: Local Assistant
version: 1.0.0
schema: v1
models:
- name: Qwen2.5-Coder 7B
provider: ollama
model: qwen2.5-coder:7b-base
apiBase: "http://localhost:11434"
roles:
- autocomplete
completionOptions:
maxTokens: 32768
contextLength: 128000
temperature: 0.6
topP: 0.8
stop:
- 'mystop'
Description
Hi, no matter how I change config.yaml, I always see temperature: 0.01 and other options unchanged for tab completion model in Continue Console. Is it a bug or I am doing something wrong?
Options
{
"model": "qwen2.5-coder:7b-base",
"maxTokens": 4096,
"temperature": 0.01,
"stop": [
"<|endoftext|>",
"<|fim_prefix|>",
"<|fim_middle|>",
"<|fim_suffix|>",
"<|fim_pad|>",
"<|repo_name|>",
"<|file_sep|>",
"<|im_start|>",
"<|im_end|>",
"/src/",
"#- coding: utf-8",
"```"
]
}
To reproduce
No response
Log output
I think the confusion here might be due to the use of completionOptions in the config.yaml file. The correct key to use is defaultCompletionOptions.
defaultCompletionOptions: the field that reads from the config and applies
completionOptions: constructed internally at runtime
This issue hasn't been updated in 90 days and will be closed after an additional 10 days without activity. If it's still important, please leave a comment and share any new information that would help us address the issue.