OFASys
OFASys copied to clipboard
OFA-Sys
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
报错download oss://ofasys/bpe/encoder.json: 0.00B [00:00, ?B/s] --------------------------------------------------------------------------- PermissionError Traceback (most recent call last) Cell In[8], [line 6](vscode-notebook-cell:?execution_count=8&line=6) [3](vscode-notebook-cell:?execution_count=8&line=3) os.environ['CUDA_VISIBLE_DEVICES'] = '1' [4](vscode-notebook-cell:?execution_count=8&line=4) from ofasys import OFASys ----> [6](vscode-notebook-cell:?execution_count=8&line=6) model = OFASys.from_pretrained('https://ofasys.oss-cn-zhangjiakou.aliyuncs.com/model_hub/multitask_10k.pt')...
the trainer cannot do the truncation by default ``` [/usr/local/lib/python3.9/dist-packages/ofasys/adaptor/general.py](https://rv8u4ubipi-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab-20230307-060233-RC01_514758488#) in concat(self, modality_outputs) 275 end_pos = start_pos + seq_length 276 if modality_output.self_attn_bias[idx] is not None: --> 277 self_attn_bias[:, :, start_pos:end_pos,...
``` bash --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) [](https://yucuju2ns5m-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab-20230307-060233-RC01_514758488#) in 1 from ofasys import Task, Trainer, GeneralistModel ----> 2 task1 = Task( 3 name='caption', 4 instruction='[IMAGE:image_url] what does the...
Feeding different boxes will always get the same outputs.
AttributeError: 'GeneralistModel' object has no attribute 'active_executor'
Closes #5 Looks like this change fixes the timeout errors. Here's [Colab notebook](https://colab.research.google.com/drive/1QiPJPmSJwegoGPZuMVt8gk9S9U9JAQU2?usp=sharing) that uses this branch. In a separate PR, I can update the notebook above and add to...
Hi, When I run the following code as shown in Readme: `model = OFASys.from_pretrained('multitask_10k.pt')` I had the following error:
Congrats on the awesome work in developing a solid framework that combines tasks and modalities. I'm impressed with the ease of combining a variety of types of input and output....
