wang-benqiang

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

lmdeploy

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

mergekit

Tools for merging pretrained large language models.

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

text-embeddings-inference

A blazing fast inference solution for text embeddings models

MoE_Train

定制化构建qwen_moe架构，并实现训练和微调

REAR

Implementation of "REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering"

InfiniTransformer

Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

open-parse

Improved file parsing for LLM’s

InternEvo

RGB

DB-GPT

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

rtp-llm

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

QAnything

Question and Answer based on Anything.

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

CodeGeeX

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

BCEmbedding

Netease Youdao's open-source embedding and reranker models for RAG products.

llama

Inference code for LLaMA models

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Firefly

Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Aurora

🐳 Aurora is a [Chinese Version] MoE model. Aurora is a further work based on Mixtral-8x7B, which activates the chat capability of the model's Chinese open domain.

YAYI

雅意大模型：为客户打造安全可靠的专属大模型，基于大规模中英文多领域指令数据训练的 LlaMA 2 & BLOOM 系列模型，由中科闻歌算法团队研发。(Repo for YaYi Chinese LLMs based on LlaMA2 & BLOOM)

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

LeetcodeTop

汇总各大互联网公司容易考察的高频leetcode题🔥

RevDet

Robust and Memory Efficient Event Detection and Tracking in Large News Feeds

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

vllm

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

vllm-cn

演示 vllm 对中文大语言模型的神奇效果