News for hackers. Stuff that matters.
Re:Uncensored LLM vision API (for internal use cases) by PLBjt on Wednesday May 08, 2024 @10:57AM (#40298800)
The safety filter of GPT 4 vision and Claude 3 Opus is critical for user facing products, but to build internal tools it impacts a lot performance (eg. to build an image moderation LLM). We had this problem internally and we had to build our own Llama 3 8B with vision (Llava architecture). We are now releasing it as an API for other developers experiencing the same issue with too censored multimodal LLM APIs.

There are no comments on this comment yet.