Projects in Awesome Lists by OFA-Sys
A curated list of projects in awesome lists by OFA-Sys .
https://github.com/ofa-sys/chinese-clip
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
chinese clip computer-vision contrastive-loss coreml-models deep-learning image-text-retrieval multi-modal multi-modal-learning nlp pretrained-models pytorch transformers vision-and-language-pre-training vision-language
Last synced: 29 Apr 2025
https://github.com/OFA-Sys/Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
chinese clip computer-vision contrastive-loss coreml-models deep-learning image-text-retrieval multi-modal multi-modal-learning nlp pretrained-models pytorch transformers vision-and-language-pre-training vision-language
Last synced: 02 Apr 2025
https://github.com/ofa-sys/ofa
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
chinese image-captioning multimodal pretrained-models pretraining prompt prompt-tuning referring-expression-comprehension text-to-image-synthesis vision-language visual-question-answering
Last synced: 15 May 2025
https://github.com/OFA-Sys/OFA
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
chinese image-captioning multimodal pretrained-models pretraining prompt prompt-tuning referring-expression-comprehension text-to-image-synthesis vision-language visual-question-answering
Last synced: 02 Apr 2025
https://github.com/OFA-Sys/ONE-PEACE
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
audio-language contrastive-loss foundation-models multimodal representation-learning vision-and-language vision-language vision-transformer
Last synced: 22 Jul 2025
https://github.com/ofa-sys/one-peace
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
audio-language contrastive-loss foundation-models multimodal representation-learning vision-and-language vision-language vision-transformer
Last synced: 13 May 2025
https://github.com/ofa-sys/gsm8k-screl
Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Last synced: 08 Jul 2025
https://github.com/ofa-sys/instag
InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning
alignment large-language-models llama llama2 natural-language-processing nlp tagging
Last synced: 03 Aug 2025
https://github.com/OFA-Sys/gsm8k-ScRel
Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Last synced: 09 May 2025
https://github.com/ofa-sys/ofasys
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
audio computer-vision deep-learning motion multimodal-learning multitask-learning nlp pretrained-models pytorch transformers vision-and-language
Last synced: 24 Oct 2025
https://github.com/ofa-sys/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".
Last synced: 13 May 2025
https://github.com/ofa-sys/touchstone
Touchstone: Evaluating Vision-Language Models by Language Models
Last synced: 07 Aug 2025
https://github.com/OFA-Sys/TouchStone
Touchstone: Evaluating Vision-Language Models by Language Models
Last synced: 11 Jul 2026
https://github.com/ofa-sys/diverseevol
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
data-centric-ai efficiency instruction-tuning large-language-models nlp self-improving
Last synced: 13 May 2025
https://github.com/ofa-sys/air-bench
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
Last synced: 27 Aug 2025
https://github.com/ofa-sys/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.
Last synced: 13 May 2025
https://ofa-sys.github.io/MoFusion/
Pretrained Diffusion Models for Unified Human Motion Synthesis
Last synced: 23 Apr 2025