Comments (1)
I can’t think of any issues running it on jetson nano, the main package you will have to install are transformers; you can find dependencies in their setup.py file. Cuda is available in got2bot and enabled by default, but the bot can be deployed on CPU devices as well. It takes a one-two seconds to generate a response without GPU; with GPU a fraction of second; this of course depends on how far is the stop token in generated response.
I’d definitely rethink setting turns_memory to unlimited since it will slow down generation process with time; values between 2 and 5 are optimal for multi turn-based chat. Number of samples of 5 will further increase processing time (up to 2-3x), and you will have to implement your own logic for selecting the best candidate sample (by default it’s done by random selection)
from gpt2bot.
Related Issues (15)
- Learning mode HOT 5
- Response Quality control HOT 1
- Can you tell on which dataset is it trained upon?
- Traning on own dataset HOT 1
- How to get gpt2bot reply message the exact length?
- Nvidia 3090 +large*-gpu.cfg HOT 1
- error when using dstc dataset in config HOT 2
- Run only on console
- It is not running in the console
- RuntimeError: CUDA error: device-side assert triggered HOT 4
- User session in Telegram supported ? HOT 2
- Transformers version HOT 2
- large model release, would you update it? HOT 7
- Flask/Gunicorn server api HOT 4
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 gpt2bot.