Add VKR CodeBERT detector model

README.md

@@ -0,0 +1,82 @@
+---
+language:
+- code
+license: mit
+base_model: microsoft/codebert-base
+tags:
+- code
+- python
+- ai-generated-code-detection
+- codebert
+- binary-classification
+pipeline_tag: text-classification
+datasets:
+- AggressiveBag/VKR_Dataset
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+---
+
+# VKR Model
+
+Binary classifier for detecting whether Python code is human-written or AI-generated.
+
+The model was fine-tuned from `microsoft/codebert-base` on the `AggressiveBag/VKR_Dataset` dataset.
+
+## Labels
+
+- `0`: human-written Python code
+- `1`: AI-generated Python code
+
+## Training Setup
+
+- Base model: `microsoft/codebert-base`
+- Maximum sequence length: 512
+- Epochs: 3
+- Batch size: 8
+- Learning rate: `2e-5`
+- Weight decay: `0.01`
+- Warmup ratio: `0.06`
+- Seed: 42
+- Encoder frozen: yes
+
+## Validation Metrics
+
+| Metric | Value |
+|---|---:|
+| Loss | 0.4192 |
+| Accuracy | 0.7836 |
+| Precision, AI class | 0.7142 |
+| Recall, AI class | 0.9456 |
+| F1, AI class | 0.8138 |
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model_id = "AggressiveBag/VKR_Model"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSequenceClassification.from_pretrained(model_id)
+
+code = "print('hello world')"
+inputs = tokenizer(code, return_tensors="pt", truncation=True, max_length=512)
+
+with torch.no_grad():
+    logits = model(**inputs).logits
+    probs = torch.softmax(logits, dim=-1)[0]
+
+print({"human": float(probs[0]), "ai": float(probs[1])})
+```
+
+## Intended Use
+
+This model is intended for research and educational experiments related to AI-generated Python code detection. It should not be used as the sole evidence for high-stakes decisions, because AI-code detection can produce false positives and false negatives.
+
+## Dataset
+
+The training data is based on human solutions from APPS and locally generated AI solutions. See `AggressiveBag/VKR_Dataset` for dataset details.

config.json

@@ -0,0 +1,38 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "ai"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "ai": 1,
+    "human": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

metrics.json

@@ -0,0 +1,7 @@
+{
+  "loss": 0.419158761295219,
+  "accuracy": 0.7836395233366436,
+  "precision_ai": 0.7142321395087193,
+  "recall_ai": 0.9456305858987091,
+  "f1_ai": 0.8138019442367269
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da991d429826fe2e45d6c9c26437163ad97bfe8aab05e7135b1b2377b1cd18c6
+size 498612824

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.json

@@ -0,0 +1,18 @@
+{
+  "train": "data\\splits\\train.jsonl",
+  "val": "data\\splits\\val.jsonl",
+  "output_dir": "runs\\codebert-ai-detector",
+  "model_name": "microsoft/codebert-base",
+  "max_length": 512,
+  "epochs": 3,
+  "batch_size": 8,
+  "gradient_accumulation_steps": 1,
+  "learning_rate": 2e-05,
+  "weight_decay": 0.01,
+  "warmup_ratio": 0.06,
+  "seed": 42,
+  "freeze_encoder": true,
+  "limit_train": null,
+  "limit_val": null,
+  "num_workers": 0
+}