| import json |
| from pathlib import Path |
|
|
| import numpy as np |
| from peft import PeftModel |
| from safetensors.numpy import load_file |
| from sentence_transformers import SentenceTransformer |
|
|
|
|
| class MuncheAIDetector: |
| def __init__(self, model_dir: str | Path = "."): |
| model_dir = Path(model_dir) |
| self.encoder = SentenceTransformer("google/embeddinggemma-300m") |
| self.encoder[0].auto_model = PeftModel.from_pretrained( |
| self.encoder[0].auto_model, |
| model_dir, |
| ) |
| self.encoder.max_seq_length = 2048 |
| head = load_file(model_dir / "linear_head.safetensors") |
| self.weight = head["linear.weight"].reshape(-1) |
| self.bias = float(head["linear.bias"].item()) |
| calibration = json.loads( |
| (model_dir / "calibration.json").read_text(encoding="utf-8") |
| ) |
| self.human_max = calibration["thresholds"]["human_max"] |
| self.ai_min = calibration["thresholds"]["ai_min"] |
|
|
| def predict(self, text: str) -> dict: |
| tokens = self.encoder.tokenizer.encode(text, add_special_tokens=False) |
| if not 384 <= len(tokens) <= 2048: |
| raise ValueError("Input must contain 384 to 2,048 EmbeddingGemma tokens.") |
| embedding = self.encoder.encode( |
| [text], |
| normalize_embeddings=True, |
| convert_to_numpy=True, |
| )[0] |
| logit = float(embedding @ self.weight + self.bias) |
| score = ( |
| float(1.0 / (1.0 + np.exp(-logit))) |
| if logit >= 0 |
| else float(np.exp(logit) / (1.0 + np.exp(logit))) |
| ) |
| label = ( |
| "human" |
| if score <= self.human_max |
| else "llm" |
| if score >= self.ai_min |
| else "uncertain" |
| ) |
| return {"label": label, "score": score, "tokens": len(tokens)} |
|
|
