garamp_qwen25_14b — Question Generation Task

Is this run manual or automatic?: automatic
Is this run based on the provided starter kit?: no
Briefly describe this run: Same pipeline as the 7B run but with Qwen2.5-14B-Instruct. ~30 candidates/topic → cleaning (≤300 chars, single question, no compound connectors) → MMR selection of the final 10. Seed=42.
What other datasets or services (e.g. Google/Bing web search, ChatGPT, Perplexity, etc.) were used in producing the run?: None. Local HF Transformers + scikit-learn only.
Briefly describe LLMs used for this run (optional): Qwen2.5-14B-Instruct, temperature=0.4, top_p=0.85, do_sample=True, no_repeat_ngram_size=4, repetition_penalty=1.1. TF-IDF + MMR (α=0.7). No finetuning.
Please give this run a priority for inclusion in manual assessments.: 2