Santacoder finetuned on Shadertoys for 1000 steps with a batch size of 2 and full sequence length of 2048. adapted finetuning script found here Main purpose of this model is to explore if finetuning models improves performance on ShaderEval, which reached 0.550 with 300 samples. While the train/test split is held out, there is a lot of data contamination. The model results can’t be trusted for this simple benchmark. Better tasks for the benchmark will be developed and tested against these models. License carried over from model, however training data has an undefied license. Check details in Shadertoys.
Модальности:
Генерация текста
Области применения:
Генерация кода
Задача: Генерация текста
Автор: Vipitis
Теги: gpt2, code, shader, custom_code, model-index, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 67
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.