This is a model based on the EleutherAI/gpt-neo-1.3B model containing 1.3 B parameters for Danish text generation. The model was not pre-trained from scratch but adapted from the English version using CLP-Transfer. Test the model using the pipeline from the 🤗 Transformers library: The training data are the Danish part of the oscar dataset (‘unshuffleddeduplicatedda’) which is split randomly into training (95%) and validation (5%) datasets. The model weights are initialized from the English gpt-neo-1.3B model (‘source model’) with new word token embeddings created from the Danish GPT-2 small model (‘helper model’) using the CLP-Transfer method. Training is done using a context window of 1024 and mixed precision (bf16). First, only the word token embeddings are trained using 0.5 M samples followed by training of all weights using approximately 2 M samples (1 epoch). The model achieves a perplexity of 16.75 on approximately 0.1 M validation samples. This is a pre-trained model, for optimal performance it should be finetuned for new downstream tasks tasks.
Модальности:
Генерация текста
Задача: Генерация текста
Автор: KennethTM
Теги: gpt_neo, da, endpoints_compatible
Лайков: 3 | Загрузок: 31
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
