Comments (3)
philschmid
commented on August 10, 2024
Hello @dennisbappert, it should be possible to use PEFT models through a custom inference.py module. See for an example on how to create a inference.py https://www.philschmid.de/custom-inference-huggingface-sagemaker
Or have you tried this already?
from sagemaker-huggingface-inference-toolkit.
dbpprt
commented on August 10, 2024
Hi @philschmid, no I haven't tried it yet but I do also think that it is possible. Integrated support however would make it much easier to use out of the box without custom inference scripts.
Likely just a feature-request for the future 👍
from sagemaker-huggingface-inference-toolkit.
philschmid
commented on August 10, 2024
Hey @dennisbappert,
Thats a great feature request, indeed! but PEFT is still pretty new lets revisit this in a few months when we have a better understanding how it is used.
from sagemaker-huggingface-inference-toolkit.
Related Issues (20)
- Using custom inference script and models from Hub HOT 1
- get_pipeline function passes Path object rather than PretrainedTokenizer
- No support for multi-GPU HOT 3
- 🏷️ invalid
- Sagemaker endpoint inferencing error with HF model loading from s3bucket with new transformer update HOT 5
- Support multiple return sequences
- HF_TASK Enviournment Variable error HOT 1
- Endpoint creation completes before custom model_fn finishes loading resources
- ARCHITECTURES_2_TASK is limiting the tasks able to be deployed with HF DLC HOT 11
- Make DEFAULT_HF_HUB_MODEL_EXPORT_DIRECTORY configurable
- Sagemaker inference not loading model weight from s3 HOT 2
- Sagemaker endpoint doesn't use GPU (instance ml.g4dn.xlarge) HOT 1
- device kernel image is invalid
- Sagemaker endpoint inference Fails when following a tutorial
- Sagemaker HuggingfaceModel fails on phi3 model deployment HOT 2
- Custom Inference Code - model_fn() takes more positional argument
- Can’t create an inference service for models that depend on packages i.e. `espeak`
- SageMaker fails because Conversation object is not found HOT 1
- How to enable Batch inference on AWS deployed Serverless model from Hub? HOT 1
- Where is the logic for detecting custom inference.py? HOT 6
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 sagemaker-huggingface-inference-toolkit.