Matt Krzus's repositories
debatrix
LLM-based Multi-dimensinal Debate Judge with Iterative Chronological Analysis
deep-research
My own open source implementation of OpenAI's new Deep Research agent. Get the same capability without paying $200. You can even tweak the behavior of the agent with adjustable breadth and depth. Run it for 5 min or 5 hours, it'll auto adjust.
entropix
Entropy Based Sampling and Parallel CoT Decoding
gmailsponge
sponge your gmail with artificial intelligence
grok
Grok open release
instructor
structured outputs for llms
kotaemon
An open-source RAG-based tool for chatting with your documents.
LightZero
[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios
linkedIn_auto_jobs_applier_with_AI
LinkedIn_AIHawk is a tool that automates the jobs application process on LinkedIn. Utilizing artificial intelligence, it enables users to apply for multiple job offers in an automated and personalized way.
llm-reasoners
A library for advanced large language model reasoning
MCTS-DPO
This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.
mergekit
Tools for merging pretrained large language models.
OpenDevin
🐚 OpenDevin: Code Less, Make More
rapid-research-framework
a research framework, but rapid.
repeng
A library for making RepE control vectors
ring-flash-attention
Ring attention implementation with flash attention
searchless_chess
Grandmaster-Level Chess Without Search
simple_transformer
Simple Transformer in Jax
simpleRL-reason
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
SPAG
Self-playing Adversarial Language Game Enhances LLM Reasoning
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.