Congfeng Cao's Projects
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
vits2 backbone with multilingual-bert
Bitcoin Core integration/staging tree
Mastering Bitcoin 3rd Edition - Programming the Open Blockchain
Config files for my GitHub profile.
FastAPI framework, high performance, easy to learn, fast to code, ready for production
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Brand new TTS solution
Free, open source crypto trading bot
This code is used to analysis CZ_Software_Mentions
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
We jailbreak GPT-3.5 Turboโs safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAIโs APIs.
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
Ongoing research training transformer models at scale
Examples in the MLX framework
Starter pack for NeurIPS LLM Efficiency Challenge 2023.
A fundational graph learning framework that solves cross-domain/cross-task classification problems using one model.
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
QLoRA: Efficient Finetuning of Quantized LLMs
This repository contains the files supporting the paper "Empowering Knowledge Discovery from Scientific Literature: A novel approach to Research Artifact Analysis".
Aligning pretrained language models with instruction data generated by themselves.
Stable Diffusion web UI
Code and documentation to train Stanford's Alpaca models, and generate the data.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Python wrapper for TA-Lib (http://ta-lib.org/).
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.