princeton-nlp/prolong-data-64K download history

princeton-nlp/prolong-data-64K is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 13,266 times (784 in the last 7 days), and 331,823 times in total. It ranks #2,355 among datasets by monthly downloads.

princeton-nlp/prolong-data-64K [Paper] [HF Collection] [Code] ProLong (Princeton long-context language models) is a family of long-context models that are continued trained and supervised fine-tuned from Llama-3-8B, with a maximum context window of 512K tokens. Our main ProLong model is o

Models trained on prolong-data-64K

10 models list it as training data.

Spaces using prolong-data-64K

Open princeton-nlp/prolong-data-64K on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.