News for hackers. Stuff that matters.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by poisson-fish on Thursday August 15, 2024 @05:08PM (#41260374)
try google's gemini models, safety filtering can be completely disabled via cloud studio or api
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by KTibow on Thursday August 15, 2024 @07:16PM (#41261501)
This is the 2nd time I've seen someone confused about this. The safety filtering is a layer on top of the model's built in ability to refuse, similar to OpenAI's "moderation" endpoint.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by og_kalu on Thursday August 15, 2024 @08:53PM (#41262058)
This is true but still Gemini is by far the least restrictive Sota LLM out there (once all safety settings are none)
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by naiv on Thursday August 15, 2024 @05:47PM (#41260732)
Looks like this is only possible with some prior manual action:

To access the BLOCK_NONE setting, you can:

Apply for the allowlist through the Gemini safety filter allowlist form,

or

Switch your account type to monthly invoiced billing with the Google Cloud invoiced billing reference.

Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by phren0logy on Thursday August 15, 2024 @05:54PM (#41260803)
No, because Google still won't explicitly clarify privacy/HIPAA-compliance on these.
Re:Hermes 3: The First Fine-Tuned Llama 3.1 405B Model by huac on Thursday August 15, 2024 @09:41PM (#41262330)
no. only 4 categories can be blocked, while the others cannot be disabled.