DeividasM/gpt2_lithuanian_small

GPT-2 model from Lithuania using Wikipedia corpus dataset based on GPT-2 small model. This is only the first version of the model; over time model will be improved using a more extensive dataset and better data preparation. This model was pre-trained with 180MB of Lithuanian Wikipedia. The texts are tokenized using a byte-level version of Byte Pair Encoding (BPE). The model was trained on wiki-corpus for 40 hours using NVIDIA Tesla P100 GPU. The training data used for this model come from Lithuanian Wikipedia. We know it contains a lot of unfiltered content from the internet, which is far from neutral. As the OpenAI team themselves point out in their model card: «Because large-scale language models like GPT-2 do not distinguish fact from fiction, we don’t support use-cases that require the generated text to be true. Additionally, language models like GPT-2 reflect the biases inherent to the systems they were trained on, so we do not recommend that they be deployed into systems that interact with humans > unless the deployers first carry out a study of biases relevant to the intended use-case. We found no statistically significant difference in gender, race, and religious bias…

Модальности:
Генерация текста

Задача: Генерация текста
Автор: DeividasM
Теги: tf, gpt2, lt, endpoints_compatible
Лайков: 3  |  Загрузок: 15

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.