OFA-Compress
OFA-Compress copied to clipboard
OFA-Sys
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 model...
Hello, Thank you for providing a clear version of the OFA model. I have a question regarding the model displayed in the image above. Is this the OFA-tiny model, or...
模型转换问题
请问，如何将下面这些pt格式的模型转化为bin格式的文件，可以基于transformers来使用？ Finetuning (OFA-Large) [Finetuned checkpoint for MUGE Caption (Stage 1)](https://ofa-beijing.oss-cn-beijing.aliyuncs.com/checkpoints/caption_cn_large.pt) [Finetuned checkpoint for RefCOCO-CN](https://ofa-beijing.oss-cn-beijing.aliyuncs.com/checkpoints/refcoco_cn_large.pt) [Finetuned checkpoint for RefCOCO+-CN](https://ofa-beijing.oss-cn-beijing.aliyuncs.com/checkpoints/refcocoplus_cn_large.pt) [Finetuned checkpoint for RefCOCOg-CN](https://ofa-beijing.oss-cn-beijing.aliyuncs.com/checkpoints/refcocog_cn_large.pt) Finetuning (OFA-Base) [Finetuned checkpoint for MUGE Caption (Stage...
Awesome job! The Huggingface version OFA looks more concise. Can this framework support multi-task pre-training like this [repo](https://github.com/OFA-Sys/OFA)? I see that this[ code file](https://github.com/OFA-Sys/OFA-Compress/blob/main/data_utils/unify_dataset.py) contains many different tasks. Could you...
