ai-and/termgrade-gemma4-31b-merged - Каталог нейросетей
Генерация текста

ai-and/termgrade-gemma4-31b-merged

Добавлено:
ai-and/termgrade-gemma4-31b-merged

Part of TermGrade: graded environments and trajectories for terminal agents. Read the blog post. 46.1 on Terminal-Bench 2.1 · +3.1 over base · no LoRA flags at serving time google/gemma-4-31B-it with the band-central adapter already merged at bf16. Adapter, methodology and caveats: ai-and/termgrade-gemma4-31b-lora. 46.1 against a 43.0 base, so +3.1, the mean of seven evaluation runs across these weights and the adapter. These weights are that adapter merged into the base, so we pool the evaluations. Across five independent training runs of the same recipe the mean is 45.1 (+2.1), SE 0.6, with all five above the base model. That is the method’s result; +3.1 is this checkpoint’s. The Artificial Analysis methodology we follow, the training recipe and the limitations are on the adapter card.

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: ai-and
Теги: gemma4_text, terminal-bench, agentic, reinforcement-learning, grpo, merged, conversational, endpoints_compatible
Лайков: 3  |  Загрузок: 173

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.