News for hackers. Stuff that matters.

A comment on Sail 7B: New Fine Tuned LLM Outperforms ChatGPT and Vicuna with Search.

Re:Sail 7B: New Fine Tuned LLM Outperforms ChatGPT and Vicun... by jmiskovic on Monday June 05, 2023 @12:42PM (#36199008)
Demo isn't really connected to the model, no way to test it out. Last commit was two weeks ago.

Did anyone reproduce the outlined steps? If this thing can be stronger than GPT-3.5 at 7B parameters (which I find unlikely), it would make bigger splash than it did.

[ Parent | on HN ]
Re:Sail 7B: New Fine Tuned LLM Outperforms ChatGPT and Vicun... by hyluo on Tuesday June 06, 2023 @01:41PM (#36216412)
Sry our backend gpu servers are being upgraded and it caused some problem for our job submission system.

Our slurm is not fixed yet, but I've brought the model back online for now - it will be temporally diabled again when our slurm is fixed.

Gradio does not allow tasks more than a minute, so the demo might fail for long texts.

[ Parent | on HN ]