---
title: ai-text-detector-qwen3-0.6b-fixed
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/ai-text-detector-qwen3-0.6b-fixed"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/ai-text-detector-qwen3-0.6b-fixed.md"
repository: AI-ModelScope/ai-text-detector-qwen3-0.6b-fixed
last_updated: 2026-08-12
license: apache-2.0
pipeline_tag: text-classification
tasks:
  - text-classification
model_type:
  - qwen3
architectures:
  - Qwen3ForSequenceClassification
base_model:
  - Qwen/Qwen3-0.6B
base_model_relation: finetune
parameters: 596.1M
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
language:
  - en
downloads: 71
stars: 0
tags:
  - ai-text-detection
  - binary-classification
  - fixed-position-readout
---

# ai-text-detector-qwen3-0.6b-fixed

> ai-text-detector-qwen3-0.6b-fixed - AI-ModelScope 在 ModelScope 开源的模型。Qwen3-0.6B Fixed-Position AI-Text Detector

AI-ModelScope/ai-text-detector-qwen3-0.6b-fixed 是 ModelScope 魔搭社区上的 596.1M 参数text-classification模型，采用 apache-2.0 许可，基于 Qwen/Qwen3-0.6B 构建。

- **Repository**: AI-ModelScope/ai-text-detector-qwen3-0.6b-fixed
- **License**: apache-2.0
- **Tasks**: text-classification
- **Parameters**: 596.1M
- **Base model**: Qwen/Qwen3-0.6B
- **Tags**: ai-text-detection, binary-classification, fixed-position-readout
- **Downloads**: 71
- **Stars**: 0
- **Last updated**: 2026-08-12

Source: https://www.modelscope.cn/models/AI-ModelScope/ai-text-detector-qwen3-0.6b-fixed

---

# Qwen3-0.6B Fixed-Position AI-Text Detector

This is a fully fine-tuned Qwen3-0.6B classifier for distinguishing human-written and AI-generated text. It uses a fixed-position readout token at the final position of a 1,024-token training context. The model was trained on [`rasbt/human-vs-ai-50k`](https://huggingface.co/datasets/rasbt/human-vs-ai-50k). Human-written text has label 0 and AI-generated text has label 1.

Temperature scaling is applied during inference. The recorded best validation accuracy was 99.96%.

 
## Download and use

```bash
hf download rasbt/ai-text-detector-qwen3-0.6b-fixed \
  --local-dir models/ai-text-detector-qwen3-0.6b-fixed
```

```python
import json
from pathlib import Path

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer


model_dir = Path("models/ai-text-detector-qwen3-0.6b-fixed")
metadata = json.loads(
    (model_dir / "detector-config.json").read_text(encoding="utf-8")
)
tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = AutoModelForSequenceClassification.from_pretrained(model_dir)
model.eval()

text = "Paste the text to classify here."
text_ids = tokenizer(
    text,
    add_special_tokens=False,
    truncation=True,
    max_length=metadata["max_text_length"],
)["input_ids"]

if metadata["readout_position"] == "fixed":
    padding_length = metadata["context_length"] - len(text_ids) - 1
    input_ids = (
        text_ids
        + [tokenizer.pad_token_id] * padding_length
        + [tokenizer.eos_token_id]
    )
    attention_mask = [1] * len(text_ids) + [0] * padding_length + [1]
else:
    input_ids = text_ids + [tokenizer.eos_token_id]
    attention_mask = [1] * len(input_ids)

inputs = {
    "input_ids": torch.tensor([input_ids]),
    "attention_mask": torch.tensor([attention_mask]),
}
with torch.inference_mode():
    logits = model(**inputs).logits / metadata["temperature"]
    probabilities = logits.float().softmax(dim=-1)

ai_index = metadata["label_mapping"]["ai"]
ai_probability = probabilities[0, ai_index].item()
print({"score": round(100 * ai_probability, 4)})
```

 
## Test-set confusion matrix

![Qwen3-0.6B fixed-position test-set confusion matrix](figures/confusion-matrix.svg)

`detector-config.json` contains the readout, calibration, and training metadata. The recommended inference implementation is provided in the [`rasbt/ai-detector`](https://github.com/rasbt/ai-detector) repository because classification requires selecting the configured readout position.

 
## Related models

- [TF-IDF logistic regression](https://huggingface.co/rasbt/ai-text-detector-logreg)
- [DistilBERT](https://huggingface.co/rasbt/ai-text-detector-distilbert)
- [DistilBERT with LoRA](https://huggingface.co/rasbt/ai-text-detector-distilbert-lora)
- [DistilBERT with MiCA](https://huggingface.co/rasbt/ai-text-detector-distilbert-mica)
- [ModernBERT](https://huggingface.co/rasbt/ai-text-detector-modernbert)
- [GPT-2 with a fixed-position readout](https://huggingface.co/rasbt/ai-text-detector-gpt2-fixed)
- [GPT-2 with a variable-position readout](https://huggingface.co/rasbt/ai-text-detector-gpt2-variable)
- [Qwen3 0.6B with a variable-position readout](https://huggingface.co/rasbt/ai-text-detector-qwen3-0.6b-variable)

 
## Limitations

Performance may change for text from generators, domains, languages, and editing workflows not represented in the training set. Short or partly AI-assisted text may also be harder to classify. The score should not be treated as definitive evidence that a person did or did not write a text.