Comments (1)
This is because Binoculars runs two 7B sized language models which could take forever on CPUs. I'm sorry but running LMs on the CPU is not recommended and this behavior is expected. I would recommend you use resources like Kaggle or Colab Notebook to get GPU access if you're constrained on resources.
You might wanna check out this HuggingFace tutorial to optimize LM inference on a CPU. Please feel free to send in PR for proper CPU support if you're able to optimize for it.
Closing this issue since not much I can do here. Thanks for your interest in the project. :)
from binoculars.
Related Issues (16)
- pip install fails HOT 1
- Link to Evaluation Datasets HOT 3
- Threshold tuning HOT 1
- How to compute AUROC using the Binocular scores? HOT 1
- Replicating Figure 4 HOT 2
- fpr threshold HOT 3
- Figure 7 HOT 3
- 1% threshold HOT 1
- cannot import Binoculars. HOT 2
- Update requirements.txt HOT 2
- Loading Falcon using legacy code HOT 1
- Pad_token not set HOT 1
- Demo no longer working HOT 1
- 4dw32241-] HOT 2
- Score variation between float32 and bfloat16 usage HOT 2
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 binoculars.