mparts/CODer-unixcoder

CODer: UniXcoder checkpoints

Fine-tuned UniXcoder classifiers that detect LLM-written Python code, trained on AIGCodeSet. They are the models behind Detecting LLM-Written Code on AIGCodeSet: Tuned Code Encoders versus N-gram Baselines. The code, the predictions and the paper are at github.com/mparts/CODer.

Layout

24 checkpoints: six seeds (seed3 to seed8) × four task variants. The paper's seed ensemble averages the six seeds' probabilities.

Folder	Task	Labels
seed<N>/binary	human vs LLM, all data	0 human, 1 ai
seed<N>/binary_generate	human vs LLM, without LLM-edited code	0 human, 1 ai
seed<N>/multiclass	human or which LLM, all data	0 Human, 1 GEMINI, 2 LLAMA, 3 CODESTRAL
seed<N>/multiclass_generate	human or which LLM, without LLM-edited code	0 Human, 1 GEMINI, 2 LLAMA, 3 CODESTRAL

The configs keep the default label names (LABEL_0, LABEL_1, ...); the table gives their meaning.

Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer

repo, variant = "mparts/CODer-unixcoder", "seed3/binary"
tok = AutoTokenizer.from_pretrained(repo, subfolder=variant)
model = AutoModelForSequenceClassification.from_pretrained(repo, subfolder=variant)

The models were trained on whitespace-normalised code (line endings unified, tabs expanded to four spaces, trailing spaces and outer blank lines removed: normalise() in src/code_origin/data/preprocess.py), truncated to 256 tokens. Normalise inputs the same way.

Training

Fine-tuned on the train split of the repository's problem-grouped split of AIGCodeSet, in which no programming problem is shared between train, dev and test: 4 epochs, learning rate 2e-5, batch size 16, max length 256, weight decay 0.01, warmup ratio 0.1. The saved weights are from the epoch with the best dev macro-F1.

Limitations

Trained on Python solutions to 317 CodeNet problems, against three LLMs (CodeLlama 34B, Codestral 22B, Gemini 1.5 Flash). It is a research artefact for this setting, not a general-purpose detector of AI-written code.

License

The weights are released under the MIT license, like the code. The training data, AIGCodeSet, is under CDLA-Permissive-2.0.