no code implementations • 26 Nov 2023 • Simon Lermen, Ondřej Kvapil
There has been increasing interest in evaluations of language models for a variety of risks and characteristics.
no code implementations • 31 Oct 2023 • Simon Lermen, Charlie Rogers-Smith, Jeffrey Ladish
With a budget of less than \$200 and using only one GPU, we successfully undo the safety training of Llama 2-Chat models of sizes 7B, 13B, and 70B and on the Mixtral instruct model.
no code implementations • 31 Oct 2023 • Pranav Gade, Simon Lermen, Charlie Rogers-Smith, Jeffrey Ladish
Llama 2-Chat is a collection of large language models that Meta developed and released to the public.
1 code implementation • 3 Jul 2023 • Teun van der Weij, Simon Lermen, Leon Lang
Recently, there has been an increase in interest in evaluating large language models for emergent and dangerous capabilities.