Expose metadata link to next version of the model 8390652 verified davanstrien HF staff commited on Sep 27, 2024
Disables inference API to prevent mismatch with HF implementation. e8a38cd gugarosa commited on Dec 13, 2023
Adds support for MQA/GQA and attention mask during training / fine-tuning. 371fd51 gugarosa commited on Oct 30, 2023