News for hackers. Stuff that matters.

kainan-ai

Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model on Thursday August 15, 2024 @06:19PM (#41261069)
Yeah it doesn't win in every category. I will say watching it in the discord I saw its performance vary widely so the context and sys prompt plays a huge role. Initially it did great and solved some pretty heavy logic questions but after the context was loaded with trolling it degraded quite a bit and couldn't solve problems it previously was able to.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model on Thursday August 15, 2024 @06:07PM (#41260955)
Yeah its on hf. You can also try it out in the Nous discord or lamda labs if you don't have the h100s to spare. Fairly certain anyone with enough compute can use it or throw it up on their site.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model on Thursday August 15, 2024 @06:03PM (#41260896)
Hermes 3 will follow the sys prompt pretty closely if you have a version where you can edit it. In the discord there were a few times it jailbroke pretty aggressively in spite of the blank system prompt.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model on Thursday August 15, 2024 @05:59PM (#41260867)
If you take the base model and put in a decent system prompt Hermes 3 405b will follow your system prompt instructions pretty well. The one in the discord has a blank system prompt and is just taking the chat as context.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model on Thursday August 15, 2024 @05:56PM (#41260827)
Yeah its more creative than other fine tunes, you'd need to make a pretty strict system prompt then test before doing anything with sensitive records
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model on Thursday August 15, 2024 @05:55PM (#41260815)
You can try it out right now in the Nous Research discord, its also up on Lambda labs' new chat thing.