Instructions to use sjiang1/codecse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sjiang1/codecse with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="sjiang1/codecse")# pip install -U transformers accelerate # Load model directly from transformers import GraphCodeBERTForCL model = GraphCodeBERTForCL.from_pretrained("sjiang1/codecse", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add "feature extraction" as our pipeline
aab1a7d -
Add a more detailed version of the inference
Add a small code snippet and more information about what is needed50bab77
-
Update README.md
be0ace7
-
Add GitHub repo for inference instructions
The GitHub repository is ready for inference!324fc41
-
Add the pretrained CodeCSE
Siyuan Jiang1. batch size 960 2. 12 epochs8155d83 -
The language should be multilingual
Siyuan JiangCodeCSE is trained for six programming languages.c2b525d -
Replace the language "ruby" with "english"
Siyuan JiangTo pass the validation process for push.68c856e -
Update the YAML content in README to pass
Siyuan Jiang2753fcc -
Add a simple readme as a Model Card.
Siyuan Jiang20da331 -
initial commit
bbe2d52