Comments (6)
Glad it works! I think I'll patch it up to automatically delete model_data if corrupted!
from onnxt5.
Hey @vladislavkoz ! Thanks for raising this.
So I have a guess as to what that might be. To start the sessions, onnxt5 first downloads and unpacks the models. If this process is incorrectly made this throws a protobuf error.
To check if it's that you can do the following:
First get the location of the package, you can simply run:
import onnxt5 print(onnxt5.__file__)
For me this gives /Users/abelriboulot/anaconda3/lib/python3.6/site-packages/onnxt5/init.py
Go to the onnxt5 package folder (in my case /Users/abelriboulot/anaconda3/lib/python3.6/site-packages/onnxt5) and cd into the model_data directory. Could you screenshot me what you see?
Then you can simply rm * and try your code again. You should see a loading bar when the models are being downloaded.
Let me know if that fixes it. If it does I might push a patch to automatically clean the model_data dir if the user has any issue.
from onnxt5.
After removing all from onnxt5 folder
Then I've removed onnxt5 using pip from my env and install it again.
During the next run, I saw a progress bar and it works well now.
Here is the onnxt5 folder after reinstallation/and the first run.
from onnxt5.
It works now. Thanks. Do you need some additional info?
from onnxt5.
Thanks for your fast help again.
from onnxt5.
@vladislavkoz I pushed 0.1.5 that should take care of this issue for future users!
from onnxt5.
Related Issues (16)
- int() argument must be a string , when running exemple. HOT 3
- Use OnnxRuntime IO Binding to improve GPU inference performance HOT 3
- Can this model suitable for multilingual-t5 accelerate? HOT 2
- quantized models HOT 1
- How to suppress output
- Inference time on gpu vs onnxt5-gpu HOT 1
- Running example "export_pretrained_model.py" as-is fails (See details) HOT 3
- cpu only inferencing
- Repeat variables assignment both
- Implement beam search HOT 2
- Can this be used with Flan-T5?
- Build a progress bar for the download of the initial files of the model
- Default T5 summary contains <extra_id_2>.<extra_id_3>.<extra_id_4> HOT 5
- Limit input ingestion to context length of the model
- Cosine similarity between embeddings HOT 7
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onnxt5.