This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess financial LLMs. Our goal is to continually push forward the open-source development of financial artificial intelligence (AI).
Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer
All documents from AlexTheAnalyst YouTube videos
[ICLR 2026] TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
Collection of important articles to be treated as a textbook
SGPT: GPT Sentence Embeddings for Semantic Search
Implementation of Statistical Learning Method, Second Edition.《统计学习方法》第二版,算法实现。
A series of top performing Text to SQL LLMs
OpenAI CLIP text encoders for multiple languages!
A high-fidelity 3D face reconstruction library from monocular RGB image(s)
- 3d-face-reconstruction
- deep-learning
- face-reconstruction
- morphable-model
Library extending Jupyter notebooks to integrate with Apache TinkerPop, openCypher, and RDF SPARQL.
- graph
- gremlin
- jupyter
- jupyter-widgets
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
Feature engineering is the process of using domain knowledge to extract features from raw data via data mining techniques. These features can be used to improve the performance of machine learning algorithms. Feature engineering can be considered as applied machine learning itself.
Book and code for Think Complexity, 2nd edition
- complex-systems
- complexity-science
- python
- textbook
🌮 Trash Annotations in Context Dataset Toolkit
[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.
Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)
AI-powered Text-to-Art Generator - Text2Art.com
- generative-art
- gan
- art
- text-to-image
In this project, I explored how to extract knowledge graphs from text using LLMs, such as OpenAI GPT4o.
BlueToolkit is an extensible Bluetooth Classic vulnerability testing framework that helps uncover new and old vulnerabilities in Bluetooth-enabled devices. Could be used in the vulnerability research, penetration testing and bluetooth hacking. We also collected and classified Bluetooth vulnerabilities in an "Awesome Bluetooth Security" way
Personalization for Stable Diffusion via Aesthetic Gradients 🎨
Generative Representational Instruction Tuning
- embeddings
- grit
- information-retrieval
- instruction-tuning
Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train your own 8B/14B LLaVA-training-like MLLM on RTX3090/4090 24GB.
- multimodal-large-language-models
- deepspeed
- model-parallel
- pipeline-parallelism
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis