News for hackers. Stuff that matters.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by oidar on Thursday August 15, 2024 @05:36PM (#41260615)
Mistrial-Nemo should be able to do this.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by fsiefken on Thursday August 15, 2024 @06:17PM (#41261049)
Mistral Large 2 is good too, if you've got the memory https://ollama.com/library/mistral-large
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by phren0logy on Thursday August 15, 2024 @05:52PM (#41260784)
This is my current go-to. It's not SOTA, but at least it does something.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by oidar on Friday August 16, 2024 @11:16AM (#41267148)
I've found that it's really good at summarizing - as it's context length is huge. Have you noticed any problems with it in that regard?