Average Model Cost: $0.0000
Number of Runs: 11,090
Models by this creator
The nbailab-base-ner-scandi model is a fine-tuned version of NbAiLab/nb-bert-base for Named Entity Recognition (NER) in Scandinavian languages. It has been trained on Danish, Norwegian, Swedish, Icelandic, and Faroese datasets. The model performs well on Scandinavian NER test datasets and is also capable of predicting English entities due to its training on English data. It is smaller and faster than previous state-of-the-art models. The model was trained using a learning rate of 2e-05, a batch size of 8, and an Adam optimizer. The training was performed for 1000 epochs using the Transformers, PyTorch, Datasets, and Tokenizers frameworks.
TExAS-SQuAD-es This model is a fine-tuned version of xlm-roberta-base on the TExAS-SQuAD-es dataset. It achieves the following results on the evaluation set: Exact match: xx.xx% F1-score: xx.xx% Training procedure Training hyperparameters The following hyperparameters were used during training: learning_rate: 2e-05 train_batch_size: 8 eval_batch_size: 8 seed: 42 gradient_accumulation_steps: 4 total_train_batch_size: 32 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lr_scheduler_type: linear num_epochs: 3 Training results Framework versions Transformers 4.12.2 Pytorch 1.8.1+cu101 Datasets 1.12.1 Tokenizers 0.10.3