AsaCooperStickland

adapter-transformers

Huggingface Transformers + Adapters = ❤️

AsaCooperStickland.github.io

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)

darts

Differentiable architecture search for convolutional and recurrent networks

hf-sharpness

Simple implementation of flat minima methods (SAM, fisher penalty) for Huggingface trainer.

latent-adversarial-training

plotting

Matplotlib talk

situational-awareness-evals

Measuring the situational awareness of language models

Spike_And_Slab

Implementation of Gibbs sampling for spike and slab priors

transparent

Exposing transformer language model internals.

AsaCooperStickland/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)

AsaCooperStickland/situational-awareness-evals

Measuring the situational awareness of language models

AsaCooperStickland/Spike_And_Slab

Implementation of Gibbs sampling for spike and slab priors

AsaCooperStickland/hf-sharpness

Simple implementation of flat minima methods (SAM, fisher penalty) for Huggingface trainer.

AsaCooperStickland/plotting

Matplotlib talk

AsaCooperStickland/transparent

Exposing transformer language model internals.

AsaCooperStickland/adapter-transformers

Huggingface Transformers + Adapters = ❤️

AsaCooperStickland/AsaCooperStickland.github.io

AsaCooperStickland/darts

Differentiable architecture search for convolutional and recurrent networks

AsaCooperStickland/latent-adversarial-training

AsaCooperStickland/FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

AsaCooperStickland/FlatMinimaInterpretability

Figuring out connections between loss landscapes and interpretability.

AsaCooperStickland/gpt3-arithmetic

Scratchpad/Chain-of-Thought Prompts

AsaCooperStickland/Ideas

Added master document and short description of SGHMC stuff

AsaCooperStickland/inverse-scaling-eval-pipeline

Basic pipeline for running different sized GPT models and plotting the results + calibration

AsaCooperStickland/knowledge-erasure

Removing knowledge from language models

AsaCooperStickland/LBM2

initlal

AsaCooperStickland/LBM_LG_code

AsaCooperStickland/llama3-jailbreak

A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

AsaCooperStickland/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.

AsaCooperStickland/memit

Mass-editing thousands of facts into a transformer memory (MEMIT)

AsaCooperStickland/mf-amazon

Matrix factorization with amazon

AsaCooperStickland/Optimizer_Visualisers

visualise ADAM and other optimzers

AsaCooperStickland/ParamEffMethods

AsaCooperStickland/ParlAI

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

AsaCooperStickland/probing_llama

Some probing experiments

AsaCooperStickland/pytorch-pretrained-BERT

A PyTorch implementation of Google AI's BERT model provided with Google's pre-trained models, examples and utilities.

AsaCooperStickland/representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

AsaCooperStickland/Spatial_Transformer

Added Adam optimiser and relu units to Lenet. Now trying to make Spatial Transformer layer work