LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

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.

BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

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.

Approximate Bayesian Computation via Population Monte Carlo and Classification

no code implementations • 29 Oct 2018 • Charlie Rogers-Smith, Henri Pesonen, Samuel Kaski

Approximate Bayesian computation (ABC) methods can be used to sample from posterior distributions when the likelihood function is unavailable or intractable, as is often the case in biological systems.

Classification General Classification