Transformers
PyTorch
code
custom_code
Inference Endpoints
codesage-small / README.md
codesage's picture
Update README.md
256829f verified
|
raw
history blame
2.23 kB
metadata
license: apache-2.0
datasets:
  - bigcode/the-stack-dedup
library_name: transformers

CodeSage-Small

Model description

CodeSage is a new family of open code embedding models with an encoder architecture that support a wide range of source code understanding tasks. It is introduced in the paper:

Code Representation Learning At Scale by Dejiao Zhang*, Wasi Uddin Ahmad*, Ming Tan, Hantian Ding, Ramesh Nallapati, Dan Roth, Xiaofei Ma, Bing Xiang (* indicates equal contribution).

Pretraining data

This checkpoint is trained on the Stack data (https://huggingface.co/datasets/bigcode/the-stack-dedup). Supported languages (9 in total) are as follows: c, c-sharp, go, java, javascript, typescript, php, python, ruby.

Training procedure

This checkpoint is first trained on code data via masked language modeling (MLM) and then on bimodal text-code pair data. Please refer to the paper for more details.

How to use

This checkpoint consists of an encoder (130M model), which can be used to extract code embeddings of 1024 dimension. It can be easily loaded using the AutoModel functionality and employs the Starcoder tokenizer (https://arxiv.org/pdf/2305.06161.pdf).

from transformers import AutoModel, AutoTokenizer

checkpoint = "codesage/codesage-small"
device = "cuda"  # for GPU usage or "cpu" for CPU usage

tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True)
model = AutoModel.from_pretrained(checkpoint, trust_remote_code=True).to(device)

inputs = tokenizer.encode("def print_hello_world():\tprint('Hello World!')", return_tensors="pt").to(device)
embedding = model(inputs)[0]
print(f'Dimension of the embedding: {embedding.size()[0]}, with norm={embedding.norm().item()}')
print(embedding)

BibTeX entry and citation info

@inproceedings{
    zhang2024codesage,
    title={CodeSage: Code Representation Learning At Scale},
    author={Dejiao Zhang* and Wasi Ahmad* and Ming Tan and Hantian Ding and Ramesh Nallapati and Dan Roth and Xiaofei Ma and Bing Xiang},
    booktitle={The Twelfth International Conference on Learning Representations},
    year={2024},
    url={https://openreview.net/forum?id=vfzRRjumpX}
}