Stars
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
Fully open reproduction of DeepSeek-R1
Open Source framework for voice and multimodal conversational AI
DSPy: The framework for programming—not prompting—language models
A modular graph-based Retrieval-Augmented Generation (RAG) system
Chat Templates for 🤗 HuggingFace Large Language Models
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Ongoing research training transformer models at scale
Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
BLEURT is a metric for Natural Language Generation based on transfer learning.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…
Set of tools to assess and improve LLM security.
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
QLoRA: Efficient Finetuning of Quantized LLMs
A high-throughput and memory-efficient inference and serving engine for LLMs
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 14+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Unified framework for building enterprise RAG pipelines with small, specialized models