liyongsea

video2dataset

Easily create large video dataset from video urls

Step-DPO

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

MetaMath-AIMO

https://www.kaggle.com/competitions/ai-mathematical-olympiad-prize/leaderboard

client-python

Python client library for Mistral AI platform

Xwin-LM

Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment

bigcodebench

BigCodeBench: The Next Generation of HumanEval

DeepSeek-Coder-V2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

MathBlackBox

lerobot

🤗 LeRobot: End-to-end Learning for Real-World Robotics in Pytorch

BunkaTopics

🗺️ Data Cleaning and Textual Data Visualization 🗺️

continue

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

mistral-finetune

llm-decontaminator

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

code-interpreter

Python & JS/TS SDK for adding code interpreting to your AI app

mistral

Workflow Service for OpenStack. Mirror of code maintained at opendev.org.

Convolutional-KANs

This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learnable non linear activations in each pixel.

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

odyssey-math

OpenDevin

🐚 OpenDevin: Code Less, Make More

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

alignment-handbook

Robust recipes to align language models with human and AI preferences

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

ai-codereviewer

AI Code Reviewer: Enhance your GitHub workflow with AI-powered code review! Get intelligent feedback and suggestions on pull requests using OpenAI's GPT-4 API, improving code quality and saving developers time.

llm-colosseum

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

hackathon

chinese-k12-evaluation

LeanCopilot

LLMs as Copilots for Theorem Proving in Lean

verbose-lean4

Natural language tactics to teach mathematics using Lean 4