An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention)

Ring attention implementation with flash attention

The official implementation of "Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks"

使用task->push实现回复大消息的示例

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financ…

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

Robust recipes to align language models with human and AI preferences

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

Structured Text Generation

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

Official inference library for Mistral models

Mamba SSM architecture

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

轩辕：度小满中文金融对话大模型

The Bytepiece Tokenizer Implemented in Rust.

Minimalist ML framework for Rust

Open source Python library for converting PDF to DOCX.

Code used for sourcing and cleaning the BigScience ROOTS corpus

Experiments on including metadata such as URLs, timestamps, website descriptions and HTML tags during pretraining.

Fast and memory-efficient exact attention

Large Language Model Text Generation Inference

A high-throughput and memory-efficient inference and serving engine for LLMs

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

Copy large files to multiple machines

Coroutine C++ Workflow based on C++ 20

A framework for few-shot evaluation of language models.