Asa Cooper Stickland's repositories
Bert-n-Pals
Pytorch implementation of Bert and Pals: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning (https://arxiv.org/abs/1902.02671)
situational-awareness-evals
Measuring the situational awareness of language models
Spike_And_Slab
Implementation of Gibbs sampling for spike and slab priors
hf-sharpness
Simple implementation of flat minima methods (SAM, fisher penalty) for Huggingface trainer.
transparent
Exposing transformer language model internals.
adapter-transformers
Huggingface Transformers + Adapters = ❤️
darts
Differentiable architecture search for convolutional and recurrent networks
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
FlatMinimaInterpretability
Figuring out connections between loss landscapes and interpretability.
gpt3-arithmetic
Scratchpad/Chain-of-Thought Prompts
Ideas
Added master document and short description of SGHMC stuff
inverse-scaling-eval-pipeline
Basic pipeline for running different sized GPT models and plotting the results + calibration
knowledge-erasure
Removing knowledge from language models
LBM2
initlal
llama3-jailbreak
A trivial programmatic Llama 3 jailbreak. Sorry Zuck!
lm-sandbox
The goal of this project is to enable users to create easy scaling law examples and cool web demos using the OpenAI GPT-3 API or Huggingface compatible LMs with just a few lines of Python.
memit
Mass-editing thousands of facts into a transformer memory (MEMIT)
mf-amazon
Matrix factorization with amazon
Optimizer_Visualisers
visualise ADAM and other optimzers
ParlAI
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
probing_llama
Some probing experiments
pytorch-pretrained-BERT
A PyTorch implementation of Google AI's BERT model provided with Google's pre-trained models, examples and utilities.
representation-engineering
Representation Engineering: A Top-Down Approach to AI Transparency
Spatial_Transformer
Added Adam optimiser and relu units to Lenet. Now trying to make Spatial Transformer layer work