OFA-Sys

All

16 repositories

ONE-PEACE
Public
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
representation-learning multimodal vision-and-language contrastive-loss vision-language vision-transformer foundation-models audio-language
Python
•
Apache License 2.0
•63•972•8•1•Updated Oct 6, 2024Oct 6, 2024
gsm8k-ScRel
Public
Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Python
•16•219•7•0•Updated Sep 12, 2024Sep 12, 2024
AIR-Bench
Public
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
Python
•3•56•5•1•Updated Aug 16, 2024Aug 16, 2024
Chinese-CLIP
Public
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
nlp computer-vision deep-learning transformers pytorch chinese pretrained-models multi-modal clip coreml-models
Python
•
MIT License
•471•4.6k•160•1•Updated Aug 6, 2024Aug 6, 2024
Ditto
Public
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".
benchmark roleplay llm
Jupyter Notebook
•
MIT License
•17•165•1•0•Updated May 28, 2024May 28, 2024
OFA
Public
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
prompt chinese image-captioning visual-question-answering multimodal text-to-image-synthesis vision-language pretraining referring-expression-comprehension prompt-tuning
Python
•
Apache License 2.0
•248•2.4k•108•3•Updated Apr 24, 2024Apr 24, 2024
TouchStone
Public
Touchstone: Evaluating Vision-Language Models by Language Models
Python
•0•78•2•0•Updated Jan 18, 2024Jan 18, 2024
DiverseEvol
Public
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
nlp efficiency self-improving data-centric-ai large-language-models instruction-tuning
Python
•2•67•2•0•Updated Dec 14, 2023Dec 14, 2023
InsTag
Public
InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning
nlp natural-language-processing tagging alignment llama large-language-models llama2
7•217•7•0•Updated Aug 20, 2023Aug 20, 2023
ExpertLLaMA
Public
An opensource ChatBot built with ExpertPrompting which achieves 96% of ChatGPT's capability.
alignment llama alpaca vicuna chatgpt
Python
•
Apache License 2.0
•22•296•1•0•Updated May 31, 2023May 31, 2023
diffusion-deploy
Public
Python
•
Apache License 2.0
•6•52•1•0•Updated Mar 12, 2023Mar 12, 2023
MoFusion
Public archive
Pretrained Diffusion Models for Unified Human Motion Synthesis
0•18•1•0•Updated Feb 28, 2023Feb 28, 2023
OFASys
Public
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
audio nlp computer-vision deep-learning motion transformers pretrained-models multimodal-learning vision-and-language multitask-learning
Python
•
Apache License 2.0
•11•144•8•1•Updated Jan 7, 2023Jan 7, 2023
Demo_CTTS
Public
present speech demo of FTTS
HTML
•0•5•0•0•Updated Nov 4, 2022Nov 4, 2022
DAFlow
Public
Python
•17•127•12•0•Updated Oct 9, 2022Oct 9, 2022
OFA-Compress
Public
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.
Python
•
Apache License 2.0
•0•27•3•0•Updated Sep 22, 2022Sep 22, 2022