On: Llama 3.1 Omni Model

[opdahl]

Any demos showcasing it’s performance?

[potatoman22 → opdahl]

There's one on Huggingface https://huggingface.co/ICTNLP/Llama-3.1-8B-Omni

[opdahl → potatoman22]

Thank you.

Obviously it doesn’t sound human but that’s extremely impressive for an 8B model. Compared to the Moshi model also on the front page now, this model seems to be more coherent, but maybe less conversational?

[twobitshifter → opdahl]

There is a demo video on the page