Chloe
Chloe
Thank you for the very cool work! I'm having trouble finding your implementation of NCE loss, however. I know @fabawi has implemented a version of this for his LoRA fine-tuning...
Thanks for this work! I'm wondering if you provide a sample script for the image to audio demo?
Hi, This is really a lovely repository. But how can I change the duration of the generated audio? Thanks!!
Hi there! I really like this repo-- thank you for creating it. How would I attempt the reverse process? i.e. creating an audio snippet based on an image?
Hi, I'm wondering how I can create a cartoon version of Yann LeCunn in the comic based on an actual photo of Yann LeCunn? Does the notebook support this?
Add DoRA support to the existing LoRA class. Includes custom test cases for DoRA, lightly adapted from those used to test LoRA. DoRA: https://arxiv.org/abs/2402.09353 FIX: https://github.com/vllm-project/vllm/issues/10849