Comments (11)
Not sure about that, maybe one of @borzunov @justheuristic @mryab knows?
from xmtf.
Hi @raihan0824,
Your GPU is not shared when you use a Petals client to run inference or fine-tuning. The GPU is only shared when you run a Petals server.
from xmtf.
yes, but I want to run bloom in petals with my own GPU, not others. Is that possible?
from xmtf.
Hi, do you mean you want to use Petals with your GPU, but don't want to let the others use it? I think you can set up a private swarm using these instructions. If you run into any troubles, the tutorial has a link to the Discord server, where we (and other users of Petals) can help you with technical issues.
Please keep in mind that you'll need around 176GB of GPU memory just for 8-bit parameters though; if you only have a single GPU, your best bet is offloading or joining the public swarm.
from xmtf.
Well noted.
Is it possible to do prompt tuning with that private swarm? also what if I want to use the smaller bloom model such as bloomz-7b1-mt?
My goal is to do prompt tuning on bloomz-7b1-mt.
from xmtf.
Yes, it is possible — you just need to specify a different set of initial peers in DistributedBloomConfig when you're creating DistributedBloomForCausalLM from the tutorial. By default, the config (and thus the model) will connect to peers from the public swarm — you need to change these to the addresses of your peers in the private swarm.
However, I'd say that for bloomz-7b1, you might not even need Petals (depends on your GPU setup, obviously). A reasonably new GPU should be able to host the whole model, so you'll be able to run it just with standard Transformers/PEFT. Do you have any specific reasons why you want to use Petals for this task?
from xmtf.
The reason why I want to use petals is because it can be used to do prompt tuning, instead of fine-tuning. I can't find other sources that provides prompt tuning for BLOOM
from xmtf.
Have you checked out https://github.com/huggingface/peft#use-cases? I think PEFT even showcases bigscience/bloomz-7b1, and the model support matrix includes BLOOM for prompt tuning
from xmtf.
Thank you for the info! Will check it out.
So I want to confirm my initial question:
It's possible to use petals with my own GPU to do inference and prompt-tuning on bigscience/bloomz-7b1 model.
Is that correct?
from xmtf.
Yes, it is possible, but not necessary: with PEFT, you are likely to get the same result with fewer intermediate steps for setup.
from xmtf.
Thank you very much 🙏
from xmtf.
Related Issues (20)
- Were the checkpoints selected based on the held-out performance or seen task performance? HOT 2
- How to convert megatron-deepspeed checkpoints to huggingface checkpoints ? HOT 4
- How to fineutne mT0 with specific down-stream data? HOT 3
- Questions on creating instruction data HOT 1
- Controlled generation HOT 1
- how to convert model weights(e.g., bigscience/bloomz-560m-optimizer-states) to Hugging Face model.bin file? HOT 2
- how to repreduce bloomz-* HOT 6
- mT0-xxl finetuning HOT 6
- bloomz-mt universal checkpoint HOT 2
- Export mt0-xxl-mt to ONNX fails HOT 2
- Dose mt0&bloomz trained on dev, devtest datasets of Flores-200? HOT 2
- Parsing the xP3 dataset HOT 1
- Getting machine-translated prompts of xP3mt HOT 4
- P3megds URL is not available HOT 1
- Some datasets are not in xP3all HOT 4
- What is the training config? HOT 3
- I can't find the model weights that you used for experimentation. HOT 1
- Quesiton about MTFDataset HOT 1
- Why does the number of templates differ between languages? 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 xmtf.