barrierye

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

parselmouth

自动化的 Python 沙箱逃逸 payload bypass 框架 / Automated Python Sandbox Escape Payload Bypass Framework

chatgpt_system_prompt

A collection of GPT system prompts and various prompt injection/leaking knowledge.

app-builder

appbuilder-sdk, 千帆AppBuilder-SDK帮助开发者灵活、快速的搭建AI原生应用

chatglm.cpp

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

ChatGLM3

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

promptflow

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

ToolBench

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

llama

Inference code for Llama models

SalesGPT

Context-aware AI Sales Agent to automate sales outreach.

tree-of-thoughts

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

Baichuan-7B

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

TigerBot

TigerBot: A multi-language multi-task LLM

zero_nlp

中文nlp解决方案(大模型、数据、模型、训练、推理)

gpt4all

GPT4All: Chat with Local LLMs on Any Device

rwkv-cpp-accelerated

A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependencies

rwkv.cpp

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

RWKV-LM-LoRA

RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

RWKV-LM-deepspeed

recurrent-memory-transformer

[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

awesome-gpt

A curated list of awesome projects and resources related to GPT, ChatGPT, OpenAI, LLM, and more.

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

GLM

GLM (General Language Model)

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

EdgeGPT

Reverse engineered API of Microsoft's Bing Chat AI

ColossalAI

Making large AI models cheaper, faster and more accessible