News for hackers. Stuff that matters.
Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by albert_e on Sunday August 13, 2023 @02:42PM (#37112808)
is there away to run this on AWS instead.

we were looking to explore Llama2 for internal use

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by froggychairs on Sunday August 13, 2023 @02:48PM (#37112888)
OpenAI models are exclusively Azure only. Llama2 should have an AWS option I believe?
Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by axpy906 on Sunday August 13, 2023 @02:49PM (#37112904)
Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by villgax on Sunday August 13, 2023 @03:06PM (#37113104)
Have your engineers set this up internally https://huggingface.co/spaces/huggingface-projects/llama-2-7...
Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by speedgoose on Sunday August 13, 2023 @03:33PM (#37113457)
You can’t really replace ChatGPT 4 with llama2 7B.
Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by villgax on Sunday August 13, 2023 @11:01PM (#37116985)
Yeah right try getting the same answer after two months
Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by klysm on Sunday August 13, 2023 @03:42PM (#37113584)
Msft spent a lot of money to ensure that was not an option w chatgpt
Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by RockyMcNuts on Sunday August 13, 2023 @10:50PM (#37116919)
https://about.fb.com/news/2023/07/llama-2/ https://huggingface.co/blog/hugging-face-endpoints-on-azure

You can of course run Llama2 in Azure, but you can't host OpenAI models in AWS

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by braydenm on Sunday August 13, 2023 @04:24PM (#37114058)
Amazon Bedrock makes Claude 2 available, as well as some other models.
Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by gdiamos on Sunday August 13, 2023 @05:06PM (#37114476)
We can run llama 2 on an AWS vm if you have enough GPUs: https://lamini.ai/

Install in 10 minutes.

Make sure you have enough GPU memory to fit your llama model if you want good perf