News for hackers. Stuff that matters.

A comment on Show HN: WhisperFusion – Ultra-low latency conversations with an AI chatbot. Parent comment

Re:Show HN: WhisperFusion – Ultra-low latency conversations ... by freeqaz on Monday January 29, 2024 @12:50PM (#39179495)
The video example is using Phi-2 which is a 2.7bn param network. I think that's part of how they're achieving the low latency here!

Has anybody fine-tuned Phi-2? I haven't found any good resources for that yet.

[ Parent | on HN ]
Re:Show HN: WhisperFusion – Ultra-low latency conversations ... by renus on Monday January 29, 2024 @01:00PM (#39179693)
We tested https://huggingface.co/cognitivecomputations/dolphin-2_6-phi... as well, in some tasks it performs better. That said, you can use Mistral as well, we support a few models through TensorRT-LLM.
[ Parent | on HN ]