w11wo/indo-gpt2-small

The model was trained on the latest (late December 2020) Indonesian Wikipedia articles . It was originally HuggingFace's pretrained English GPT-2 model and is later fine-tuned on the Indonesian dataset . PyTorch was used as the backend framework during training, but the model remains compatible with TensorFlow . Many of the techniques used are based on a notebook/blog shared by Pierre Guillou . The model may not always generate factual texts and the biases which came from the Wikipedia articles may be carried over into the results of this model . All computation and development are done on Google Colaboratory using their GPU access, using their free free-market access to the model .,