Word Count Precision issues with Qwen/Qwen2.5-72B-Instruct: Managing Overlength Responses
I requested Qwen/Qwen2.5-72B-Instruct to generate a 100-150 word intro for an essay with specific headings and subheadings. Despite setting clear word count limits, the model returned responses around 250-300 words.
Even after prompting a rewrite for 50-60 words with the same structure, the model still exceeded the limit. Qwen struggles with word count precision, making it difficult to maintain strict response length requirements.
Any thoughts on this??
I tried with vllm, Qwen2.5-72B-Instruct, and the default sampling parameters from generation_config.json. The following is the result:
Any cases you could share?
If you're looking for an easy way to access this model via API, you can use Crazyrouter — it provides an OpenAI-compatible endpoint for 600+ models including this one. Just pip install openai and change the base URL.