---
title: anah-20b
canonical_url: "https://www.modelscope.cn/models/opencompass/anah-20b"
md_url: "https://www.modelscope.cn/models/opencompass/anah-20b.md"
repository: opencompass/anah-20b
last_updated: 2025-03-08
license: apache-2.0
pipeline_tag: text-classification
tasks:
  - text-classification
model_type:
  - internlm2
architectures:
  - InternLM2ForCausalLM
parameters: 19.9B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1724
stars: 0
tags:
  - hallucination-detection
  - text-classification
---

# anah-20b

> anah-20b - opencompass 在 ModelScope 开源的模型。ANAH: Analytical Annotation of Hallucinations in Large Language Models

opencompass/anah-20b 是 ModelScope 魔搭社区上的 19.9B 参数text-classification模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: opencompass/anah-20b
- **License**: apache-2.0
- **Tasks**: text-classification
- **Parameters**: 19.9B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: hallucination-detection, text-classification
- **Downloads**: 1724
- **Stars**: 0
- **Last updated**: 2025-03-08

Source: https://www.modelscope.cn/models/opencompass/anah-20b

---

# ANAH: Analytical Annotation of Hallucinations in Large Language Models

[![arXiv](https://img.shields.io/badge/arXiv-2312.14033-b31b1b.svg)](https://arxiv.org/abs/2405.20315)
[![license](https://img.shields.io/github/license/InternLM/opencompass.svg)](./LICENSE)

This page holds the InternLM2-20B model which is trained with the ANAH dataset. It is fine-tuned to annotate the hallucination in LLM's responses.

More information please refer to our [project page](https://open-compass.github.io/ANAH/).

## 🤗 How to use the model

You have to follow the prompt in [our paper](https://arxiv.org/abs/2405.20315) to annotate the hallucination.

The models follow the conversation format of InternLM2-chat, with the template protocol as:

```python
dict(role='user', begin='<|im_start|>user
', end='<|im_end|>
'),
dict(role='assistant', begin='<|im_start|>assistant
', end='<|im_end|>
'),
```

## 🖊️ Citation

If you find this project useful in your research, please consider citing:
```
@article{ji2024anah,
  title={ANAH: Analytical Annotation of Hallucinations in Large Language Models},
  author={Ji, Ziwei and Gu, Yuzhe and Zhang, Wenwei and Lyu, Chengqi and Lin, Dahua and Chen, Kai},
  journal={arXiv preprint arXiv:2405.20315},
  year={2024}
}
```