AQuarterMile/WritingBench-Critic-Model-Qwen-7B

📃 [Paper] • 🚀 [Github Repo] • 📏 [Critic Model] • ✍️ [Writer-7B] [Writer-32B] This model is fine-tuned from Qwen/Qwen2.5-7B-Instruct on a 50K SFT dataset for writing evaluation tasks. For each criterion, the evaluator independently assigns a score on a 10-point scale to a response, providing both a score and a justification. The following hyperparameters were used during training: — learningrate: 7e-06 — trainbatchsize: 1 — evalbatchsize: 8 — seed: 42 — distributedtype: multi-GPU — numdevices: 8 — gradientaccumulationsteps: 8 — totaltrainbatchsize: 64 — totalevalbatchsize: 64 — optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments — lrschedulertype: cosine — lrschedulerwarmupratio: 0.1 — num_epochs: 3 — Transformers 4

Модальности:
Генерация текста

Области применения:
Диалог / чат

Задача: Генерация текста
Автор: AQuarterMile
Теги: qwen2, llama-factory, generated_from_trainer, conversational, text-generation-inference, endpoints_compatible
Лайков: 3  |  Загрузок: 582

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.