LoRA adapter fine-tuned from Qwen/Qwen3-8B for collaborative creative writing (poems, short stories) with the DiscoverLLM training framework (paper · project page). DiscoverLLM trains LLMs to help users figure out what they want by modeling intent discovery as the reward signal, then optimizing against a simulator that maintains a latent intent hierarchy. Trained with GRPO on kixlab/DiscoverLLM-multiturn-preferences using TRL and PEFT. > Note: the base model Qwen/Qwen3-8B may be gated. > You need to accept its license on the Hub before this adapter will load. — Method: GRPO (offline) via TRL. DiscoverLLM uses the standard Group Relative Policy Optimization (GRPO; Shao et al., 2024) algorithm; the contribution is the simulator-derived reward. — Adapter: LoRA (r=32, alpha=64; all attention + MLP projections) — Framework versions: PEFT 0.18.0 / TRL 0.26.2 / Transformers 4.57.4 / PyTorch 2.9.0
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: kixlab
Теги: peft, lora, grpo, trl, multi-turn, intent-discovery, conversational, en
Лайков: 3 | Загрузок: 31
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
