Add an option to set the max_tokens_to_sample parameter
Closed this issue · 1 comments
tomviner commented
https://docs.anthropic.com/claude/reference/complete_post
This is currently hardcoded to 300 at https://github.com/tomviner/llm-claude/blob/0.2/llm_claude/__init__.py#L43
What's a good default? Or strategy to set it dynamically?
tomviner commented