Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!
MIT License
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and b...
An Open-sourced Knowledgable Large Language Model Framework.
A one-stop data processing system to make data higher-quality, juicier, and more digestible for (...
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet ...
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
AirLLM 70B inference with single 4GB GPU
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训...
Instruction Tuning with GPT-4
Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Fal...
LLaVA-NeXT-Image-Llama3-Lora, Modified from https://github.com/arielnlee/LLaVA-1.6-ft
[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language M...
Multimodal-GPT
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback