Comments (9)
trlx is not designed for colab usage. iirc there is an available colab notebook floating around the open assistant discord server. This notebook is not officially endorsed. https://colab.research.google.com/drive/11CTcGVXYK6XLN8KpulcEkehTA1Au8f2o?usp=sharing
from trlx.
It works in colab but colab is not a platform that we actively go out of our way to support. TRLX is designed for super computers. it would be the equivalent of trying to get Megatron or NeoX working in colab. I am sure you could do it with enough effort, but I don't see the use case.
from trlx.
Untarred the v0.2 release, and did not encounter the same error there. Curious.
from trlx.
Cannot repro. Talked with @alat-rights on discord. Closing issue. Will reopen if others report similar problems.
from trlx.
I'm facing the same problem on colab
from trlx.
Thank you, would you be able to outline conflicts and problems for using in colab, maybe I can resolve them!
from trlx.
If you use the colab notebook above, for instance, there is no multinode or multigpu support since trlx's accelerate implementation tends to not play nicely with colab. You can use colab fine for single gpu stuff at the moment..
from trlx.
You are right, unfortunately this notebook also would not rum on colab.
from trlx.
You probably have some installation issue. I just checked the notebook and it runs. Make sure to restart the colab after you install the package.
from trlx.
Related Issues (20)
- multigpu support for summarization ppo example HOT 3
- Support parallel reward_fn in PPO training
- resume_from_checkpoint doesn't work HOT 1
- Issue since most recent transformers update HOT 1
- Multi-GPU training errors with peft HOT 1
- Attention mask when calculating log ratio for PPO
- when i use trlx ppotrainer train a model llama 13b model, but saved huggingface mode ,but when it inference , it has some strange keys ,and the inference result did not show ,it also have no error , it seems the result disapper HOT 1
- MPT is not working
- Runtime error when running examples (ilql_sentiments_t5.py) HOT 2
- Integration of Self-Play Fine-Tuning (SPIN) Method for Enhancing Large Language Models
- RLHF text summarization diverges
- [New Feature Request] Add KTO
- Issue of tensors share memory HOT 1
- TRLX Environment customization
- Why train dataloader is not prepared by Accelerator
- Data Loader Bug when running t5_summarization_daily_cnn.py
- Crash when using save_state with deepspeed: `model.state_dict` functions incompatible with new deepspeed.
- Error when running Ray Tune to launch hyperparameter sweep HOT 1
- maybe bug in prepare & load's order HOT 1
- cannot import name 'flatten_dataclass' from 'trlx.data.ilql_types'
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 trlx.