Crosslingual Generalization through Multitask Finetuning

A curated list of Large Language Model (LLM) Interpretability resources.

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

[ICLR'24 spotlight] Tool-Augmented Reward Modeling

A framework for the evaluation of autoregressive code generation language models.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Critique-out-Loud Reward Models

My collection of machine learning papers

Awesome Incremental Learning

Efficient Triton Kernels for LLM Training

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

An extremely fast Python package and project manager, written in Rust.

Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"

[ACL2024 Findings]DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling

Build Conversational AI in minutes ⚡️

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

Apps/CLIs/configs I use on macOS/iOS. Fish, Karabiner, Cursor..

A tool that bootstraps your dotfiles ⚡️

🇫🇷 Oh my tmux! My self-contained, pretty & versatile tmux configuration made with ❤️

config files for zsh, bash, completions, gem, git, irb, rails

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, and more with your permission every step of the way.

CodeRAG-Bench: Can Retrieval Augment Code Generation?

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

WIP - Allows you to create DSPy pipelines using ComfyUI

Structured Text Generation

SGLang is a fast serving framework for large language models and vision language models.