This is your work, valued
PhD Student in Natural Language Processing at the University of Edinburgh
bpeasy. Fast bare-bones BPE for modern tokenizer training
179plancraft. Plancraft is a minecraft environment and agent suite to test planning capabilities in LLMs
30tokenizer-bench. Code for the paper "Getting the most out of your tokenizer for pre-training and domain adaptation"
22kblaunch. CLI for fast launching jobs on a Kubernetes research cluster 🛸
15pytorch-attentive-lm. Pytorch Implementation of an A-RNN-LM
13cultural-evolution-engine. This is a first take at a task and model agnostic CEE
5pytorch-research-template. Opinionated Research Template
3pcfg-attention. Using an Attention Seq-to-Seq model on pcfg
3batche. Batch cache decorator
2learnability-communication-tradeoff. learnability-communication-tradeoff
2rsa-a. A deeper dive into Representational Similarity Analysis in Referential Games
2cast. Python
2riiid. Repo for RIIID Kaggle competition
2Awesome-LVLM-Hallucination. up-to-date curated list of state-of-the-art Large vision language models hallucinations research work, papers & resources
1machine-tasks. Datasets for compositional learning
1flag-vscode-extension. VS code extension for flags
1awesome-constrained-decoding. List of open-source constrained decoding projects
1serverless-plugin-ts-validation. Serverless plugin to generate validation JSON schemas from Typescript interfaces
1pythondatastruc. Python Data Structures - simple implementations
1