Tomek Korbak's starred repositories
gpt-repository-loader
Convert code repos into an LLM prompt-friendly format. Mostly built by GPT-4.
inspect_ai
Inspect: A framework for large language model evaluations
devika
Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.
torchtitan
A native PyTorch Library for large model training
posteriors
Uncertainty quantification with PyTorch
machine-learning-list
A curriculum for learning about foundation models, from scratch to the frontier
min-max-gpt
Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
scattermoe
Triton-based implementation of Sparse Mixture of Experts.
Triton-Puzzles
Puzzles for learning Triton
llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
llm-hallucination-survey
Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"
sycophancy-eval
datasets from the paper "Towards Understanding Sycophancy in Language Models"
representation-engineering
Representation Engineering: A Top-Down Approach to AI Transparency
anthropic-cookbook
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
Neuro_AI_Papers
A curated repository of Neuro-AI papers.
situational-awareness-evals
Measuring the situational awareness of language models
lm-human-preference-details
RLHF implementation details of OAI's 2019 codebase