The LLM Evaluation Framework

LLM101n: Let's build a Storyteller

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Kimi K2 is the large language model series developed by Moonshot AI team

Notepad++ official repository

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Scaling Preference Data Curation via Human-AI Synergy

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

Code for ICML 2025 paper "GRAM: A Generative Foundation Reward Model for Reward Generalization"

[ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

In this repository, we provide generative foundation reward models to produce more accurate reward scores, thereby enabling better alignment of LLMs.

Python library to use Pleias-RAG models

The hub for EleutherAI's work on interpretability and learning dynamics

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / veRL/ Swift / Ultra…

Supercharge Your Model Training

Bringing BERT into modernity via both architecture changes and scaling

Lightweight coding agent that runs in your terminal

A programming framework for agentic AI

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced a…

Supercharge Your LLM Application Evaluations 🚀

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Reproduce R1 Zero on Logic Puzzle

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Integrate the DeepSeek API into popular softwares

This is the repo for the LegalBench-RAG Paper: https://arxiv.org/abs/2408.10343.