Stars
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
Renderer for the harmony response format to be used with gpt-oss
MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining
A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Unleashing the Power of Reinforcement Learning for Math and Code Reasoners
L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
Chat language model that can use tools and interpret the results
[ACL 2025 Main] Repository for the paper: 500xCompressor: Generalized Prompt Compression for Large Language Models
Utilities intended for use with Llama models.
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Multimodal language model benchmark, featuring challenging examples
RepoQA: Evaluating Long-Context Code Understanding
Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.
Code examples and jupyter notebooks for the Cohere Platform
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Function Calling Mistral 7B. Learn how to make functions call for open source LLMs.