1 citations · 1 across the 2 of their papers we have counts for
6 papers
Ministral 3
Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian +116
We introduce the Ministral 3 series, a family of parameter-efficient dense language models designed for compute and memory constrained applications, available in three model sizes:…
Learning to Skip the Middle Layers of Transformers
Tim Lawson, Laurence Aitchison
Conditional computation is a popular strategy to make Transformers more efficient. Existing methods often target individual modules (e.g., mixture-of-experts layers) or skip layers…
Massively Parallel Expectation Maximization For Approximate Posteriors
Thomas Heap, Sam Bowyer, Laurence Aitchison
Bayesian inference for hierarchical models can be very challenging. MCMC methods have difficulty scaling to large models with many observations and latent variables. While variatio…
Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
Sam Bowyer, Laurence Aitchison, Desi R. Ivanova
Rigorous statistical evaluations of large language models (LLMs), including valid error bars and significance testing, are essential for meaningful and reliable performance assessm…
Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
Lucy Farnik, Tim Lawson, Conor Houghton +1
Sparse autoencoders (SAEs) have been successfully used to discover sparse and human-interpretable representations of the latent activations of LLMs. However, we would ultimately li…
Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers
Thomas Heap, Tim Lawson, Lucy Farnik +1
Sparse autoencoders (SAEs) are widely used to extract sparse, interpretable latents from transformer activations. We test whether commonly used SAE quality metrics and automatic ex…