Sileod
Rank:Average Model Cost: $0.0000
Number of Runs: 33,381
Models by this creator
deberta-v3-large-tasksource-nli
deberta-v3-large-tasksource-nli
deberta-v3-large-tasksource-nli is a zero-shot classification model based on DeBERTa, a transformer-based language model. The model can classify text into different categories without requiring training on specific examples of each category. It is useful for tasks such as text classification, document ranking, and natural language understanding.
$-/run
18.8K
Huggingface
deberta-v3-base-tasksource-nli
deberta-v3-base-tasksource-nli
DeBERTa-v3-base-tasksource-nli is a model that has been fine-tuned using multi-task learning on 600 tasks from the tasksource collection. It performs well in zero-shot validation on various tasks and can be used for zero-shot entailment-based classification pipeline, natural language inference, and other tasks using tasksource-adapters. The model's training data includes a specially constructed NLI dataset to improve zero-shot classification. It ranked 1st among all models with the microsoft/deberta-v3-base architecture according to the IBM model recycling evaluation. The model's code and training details are available on GitHub, and the author can be contacted for more information.
$-/run
13.6K
Huggingface
mdeberta-v3-base-tasksource-nli
mdeberta-v3-base-tasksource-nli
Model Card for mDeBERTa-v3-base-tasksource-nli Multilingual mdeberta-v3-base with 30k steps multi-task training on mtasksource This model can be used as a stable starting-point for further fine-tuning, or directly in zero-shot NLI model or a zero-shot pipeline. In addition, you can use the provided adapters to directly load a model for hundreds of tasks. For more details, see deberta-v3-base-tasksource-nli and replace tasksource by mtasksource. Software https://github.com/sileod/tasksource/ https://github.com/sileod/tasknet/ Contact and citation For help integrating tasksource into your experiments, please contact damien.sileo@inria.fr. For more details, refer to this article:
$-/run
737
Huggingface
roberta-base-discourse-marker-prediction
$-/run
156
Huggingface
deberta-v3-base-tasksource-adapters
deberta-v3-base-tasksource-adapters
Platform did not provide a description for this model.
$-/run
89
Huggingface
deberta-v3-large-tasksource-rlhf-reward-model
deberta-v3-large-tasksource-rlhf-reward-model
Platform did not provide a description for this model.
$-/run
47
Huggingface
roberta-base-random
$-/run
10
Huggingface
deberta-v3-large-tasksource-adapters
$-/run
9
Huggingface