OFA-Sys

Chinese-CLIP

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

OFA

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

ONE-PEACE

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

ExpertLLaMA

An opensource ChatBot built with ExpertPrompting which achieves 96% of ChatGPT's capability.

gsm8k-ScRel

Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

OFASys

OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models

DAFlow

InsTag

InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning

Ditto

A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".

TouchStone

Touchstone: Evaluating Vision-Language Models by Language Models

DiverseEvol

Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning

diffusion-deploy

OFA-Compress

OFA-Compress is a unified framework which provides OFA model finetuning, distillation and inference capabilities in Huggingface version, and is committed to promoting the lightweighting of large models.

MoFusion

Pretrained Diffusion Models for Unified Human Motion Synthesis

Demo_CTTS

present speech demo of FTTS