🦜🔗 Build context-aware reasoning applications

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

🔊 Text-Prompted Generative Audio Model

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

A game theoretic approach to explain the output of any machine learning model.

StableLM: Stability AI Language Models

llama3 implementation one matrix multiplication at a time

Code for Machine Learning for Algorithmic Trading, 2nd edition.

Automatic extraction of relevant features from time series:

[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

An adversarial example library for constructing attacks, building defenses, and benchmarking both

中文nlp解决方案(大模型、数据、模型、训练、推理)

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

New ways of breaking app-integrated LLMs

TruthfulQA: Measuring How Models Imitate Human Falsehoods

Data and code for FreshLLMs (https://arxiv.org/abs/2310.03214)

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

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

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models