kindaQ

flash-attention

Fast and memory-efficient exact attention

ms-swift

Use PEFT or Full-parameter to finetune 300+ LLMs or 60+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

SpecAugment

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Qwen-Audio

The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

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.

RyzenAI-SW

HTTP_SERVER

基于python实现http服务器，支持文件夹/文件上传和下载

doccano

Open source annotation tool for machine learning practitioners.

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

llama_index

LlamaIndex is a data framework for your LLM applications

langchain

🦜🔗 Build context-aware reasoning applications

ChatGLM3

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

vision_transformer

diffusion

Denoising Diffusion Probabilistic Models

long_llama

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

NExT-GPT

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

vllm

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

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

chatglm.cpp

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

BIG-Bench-Hard

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型