uuzna's Stars
OpenCodeInterpreter/OpenCodeInterpreter
OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.
uiuc-focal-lab/syncode
Efficient and general syntactical decoding for Large Language Models
predibase/lorax
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
NVIDIA/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.
hpcaitech/Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
facefusion/facefusion
Next generation face swapper and enhancer
anothermartz/Easy-Wav2Lip
Colab for making Wav2Lip high quality and easy to use
containers/bubblewrap
Low-level unprivileged sandboxing tool used by Flatpak and similar projects
RVC-Boss/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
yerfor/GeneFacePlusPlus
GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code
chatchat-space/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
THUDM/ChatGLM3
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
Codium-ai/AlphaCodium
Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""
HumanAIGC/AnimateAnyone
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
onejune2018/Awesome-LLM-Eval
Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表,主要面向基础大模型评测,旨在探求生成式AI的技术边界.
PlayVoice/whisper-vits-svc
Core Engine of Singing Voice Conversion & Singing Voice Clone
zju3dv/Mirror-NeRF
Code for "Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracing", ACM MM 2023
openai/human-eval
Code for the paper "Evaluating Large Language Models Trained on Code"
uuzna/GQUPT
一款基于openai GPT api的windows问答软件,支持GPT3.5和GPT4, 无需翻墙真香
MaaAssistantArknights/MaaAssistantArknights
《明日方舟》小助手,全日常一键长草!| A one-click tool for the daily tasks of Arknights, supporting all clients.
Nemo2011/bilibili-api
哔哩哔哩常用API调用。支持视频、番剧、用户、频道、音频等功能。原仓库地址:https://github.com/MoyuScript/bilibili-api
labring/FastGPT
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
lm-sys/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
binary-husky/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。
microsoft/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
voicepaw/so-vits-svc-fork
so-vits-svc fork with realtime support, improved interface and more features.
svc-develop-team/so-vits-svc
SoftVC VITS Singing Voice Conversion
openai/evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
chenfei-wu/TaskMatrix
google-research/tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.