Data-centric LLM training with dynamic sample selection, domain mixture optimization, and example reweighting inside the LLaMA-Factory training loop.

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

Aligning LMMs with Factually Augmented RLHF

Utilities intended for use with Llama models.

Inference code for Llama models

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Code and documentation to train Stanford's Alpaca models, and generate the data.

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

A multi document reader and chatbot using LangChain and ChatGPT

LAVIS - A One-stop Library for Language-Vision Intelligence

The agent engineering platform.

A package which efficiently applies any function to a pandas dataframe or series in the fastest available manner

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

LLaMA: Open and Efficient Foundation Language Models

Artificial Intelligence projects, documentation and code.

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

A lightweight conic solver for second-order cone programming.

A Python-embedded modeling language for convex optimization problems.

PLDA: Parallel Latent Dirichlet Allocation in C++

A repository to prove the Bayesian Label Smoothing theory proposed by my Master's thesis

CNCF sandbox project, an open source distributed time-series database with high concurrency, high performance, and high scalability

This is a curated list for Information Bottleneck Principle, in memory of Professor Naftali Tishby.

Non-parametric Entropy Estimation Toolbox

explore DNNs via Infomration

Code for "Self-Distillation as Instance-Specific Label Smoothing"

Fastest Gephi's ForceAtlas2 graph layout algorithm implemented for Python and NetworkX

A robust & multipurpose Graph object for JavaScript & TypeScript.

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接