bbo0924

ToolSandbox

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

sglang

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

mem0

The memory layer for Personalized AI

LLM101n

LLM101n: Let's build a Storyteller

AIOS

AIOS: LLM Agent Operating System

OpenAGI

OpenAGI: When LLM Meets Domain Experts

JioNLP

中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com

cosmopedia

EasyNLP

EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

dive-into-llms

《动手学大模型Dive into LLMs》系列编程实践教程

llama2.c

Inference Llama 2 in one file of pure C

qserve

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

TensorRT-LLM

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 efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

llama-cpp-python

Python bindings for llama.cpp

LLM-Tuning

Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.

distilling-step-by-step

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

llm-course

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

ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

llm.c

LLM training in simple, raw C/CUDA

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

NexusRaven

NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRaven-13B and baselines.

ChatGPTX-Uni

实现一种多Lora权值集成切换+Zero-Finetune零微调增强的跨模型技术方案，LLM-Base+LLM-X+Alpaca，初期，LLM-Base为Chatglm6B底座模型，LLM-X是LLAMA增强模型。该方案简易高效，目标是使此类语言模型能够低能耗广泛部署，并最终在小模型的基座上发生“智能涌现”，力图最小计算代价达成ChatGPT、GPT4、ChatRWKV等人类友好亲和效果。当前可以满足总结、提问、问答、摘要、改写、评论、扮演等各种需求。

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)