asacooperstickland Goto Github PK
Name: Asa Cooper Stickland
Type: User
Bio: Doing a machine learning/NLP PhD at Edinburgh University.
Twitter: AsaCoopStick
Location: Edinburgh, United Kingdom
Name: Asa Cooper Stickland
Type: User
Bio: Doing a machine learning/NLP PhD at Edinburgh University.
Twitter: AsaCoopStick
Location: Edinburgh, United Kingdom
Huggingface Transformers + Adapters = ❤️
Pytorch implementation of Bert and Pals: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning (https://arxiv.org/abs/1902.02671)
Differentiable architecture search for convolutional and recurrent networks
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Figuring out connections between loss landscapes and interpretability.
Scratchpad/Chain-of-Thought Prompts
Simple implementation of flat minima methods (SAM, fisher penalty) for Huggingface trainer.
Added master document and short description of SGHMC stuff
Basic pipeline for running different sized GPT models and plotting the results + calibration
Removing knowledge from language models
initlal
A trivial programmatic Llama 3 jailbreak. Sorry Zuck!
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.
Mass-editing thousands of facts into a transformer memory (MEMIT)
Matrix factorization with amazon
visualise ADAM and other optimzers
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
Matplotlib talk
Some probing experiments
A PyTorch implementation of Google AI's BERT model provided with Google's pre-trained models, examples and utilities.
Representation Engineering: A Top-Down Approach to AI Transparency
Measuring the situational awareness of language models
Added Adam optimiser and relu units to Lenet. Now trying to make Spatial Transformer layer work
Implementation of Gibbs sampling for spike and slab priors
Exposing transformer language model internals.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.