dpimagine

mem0

The Memory layer for your AI apps

llama-recipes

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

semgrep

Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Qwen-VL

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

llama-stack-apps

Agentic components of the Llama Stack APIs

PurpleLlama

Set of tools to assess and improve LLM security.

weggli

weggli is a fast and robust semantic search tool for C and C++ codebases. It is designed to help security researchers identify interesting functionality in large codebases.

bookget

bookget 数字古籍图书下载工具

sacrebleu

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

MobileLLM

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

MiniGPT-4-ZH

MiniGPT-4 中文部署翻译 完善部署细节

AgentSims

AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.

rtvi-web-demo

Example UI implementing the RTVI web client

FlagGems

FlagGems is an operator library for large language models implemented in Triton Language.

unibench

Python Library to evaluate VLM models' robustness across diverse benchmarks

EvalCrafter

[CVPR 2024] EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

ianvs

Distributed Synergy AI Benchmarking

SuperCLUE-Safety

SC-Safety: 中文大模型多轮对抗安全基准

SuperCLUE-RAG

中文原生检索增强生成测评基准

MMTrustEval

A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)

amber-data-prep

Data preparation code for Amber 7B LLM

LLM4CP

SuperCLUE-Auto

汽车行业中文大模型测评基准，基于多轮开放式问题的细粒度评测

NewsBench

[ACL 2024 Main] NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism

sora-prompt-zh

Sora 中文的提示词 | 短视频提示词（prompt）技巧 | 调教指南。各种场景使用指南。学习怎么让它听你的话。兼顾了 Sora 的多场景应用。

SuperCLUE-Video

中文原生多层次文生视频测评基准

HalluDial

hpcbenchmarks

高性能计算系统性能评价工具集

SuperCLUE-V

中文原生多模态理解测评基准（测评方案）