[ACL 2024] Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Generative Judge for Evaluating Alignment

.NET news, announcements, release notes, and more!

Dataset and code for EMNLP2020 paper "HybridQA: A Dataset of Multi-Hop Question Answeringover Tabular and Textual Data"

Starter-kit to build constrained agents with Nextjs, FastAPI and Langchain

[ACL'24 Oral] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark

Official repo for SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency

Landmark Attention: Random-Access Infinite Context Length for Transformers

Ready-to-use SRT / WebRTC / RTSP / RTMP / LL-HLS media server and media proxy that allows to read, publish, proxy, record and playback video and audio streams.

A cloud-native vector database, storage for next generation AI applications

Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)

Measuring Massive Multitask Language Understanding | ICLR 2021

CLI tool for spawning and running containers according to the OCI specification

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

The Ethereum Improvement Proposal repository

A framework for few-shot evaluation of language models.

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Run Mixtral-8x7B models in Colab or consumer desktops

An Artificial Intelligence Automation Platform. AI Instruction management from various providers, has an adaptive memory, and a versatile plugin system with many commands including web browsing. Su…

a better universal ui system

Wechat robot based on ChatGPT, which using OpenAI api and itchat library. 使用ChatGPT搭建微信聊天机器人，基于GPT3.5/4.0 API和itchat实现，能处理文本、语音和图片，访问操作系统和互联网。

Babylon.js is a powerful, beautiful, simple, and open game and rendering engine packed into a friendly JavaScript framework.

ChatGPT interface with better UI + running on free gpt api's