gpt2-medium · azureml v10 ↗
- source model id
- azureml/gpt2-medium@10
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- mit
- architecture
- input_modalities
- text
- output_modalities
- text
- capabilities
The GPT-2 Transformer-based language model is designed primarily for use by AI researchers and practitioners. The intended uses of the language model include understanding the behavior, capability, b…
azureFoundry/azureml/gpt2-medium@10
The GPT-2 Transformer-based language model is designed primarily for use by AI researchers and practitioners. The intended uses of the language model include understanding the behavior, capability, biases, and constraints of large-scale generative language models. Secondary use cases of the language model include writing assistance, creative writing and art, and entertainment. The model is trained on a big corpus of English data, but the training data has not been released for public browsing. The authors of the model do not support use of the model to generate text that requires truth, nor do they recommend deployment of the language model in systems that interact with humans because of the biases inherent in the model. The model was pretrained on raw texts in a self-supervised manner with an automatic process that generates inputs and labels based on the words in the texts. The inputs were tokenized using byte-level pairing encoding with a vocabulary size of 50,257 and a sequence len
1–1 / 1
1–3 / 3
Microsoft Foundry · Model page ↗
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.