Add missing metadata and clarify license (#1)

- Add missing metadata and clarify license (d9b5b3a1d17b6d7ae0e766acf993d966f6c45857)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,6 +1,17 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-classification
+tags:
+- hallucination-detection
+- text-classification
+language:
+- en
+---
+
 # 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)
+[![arXiv](https://img.shields.io/badge/arXiv-2405.20315-b31b1b.svg)](https://arxiv.org/abs/2405.20315)
 [![license](https://img.shields.io/github/license/InternLM/opencompass.svg)](./LICENSE)
 
 This page holds the InternLM2-7B model which is trained with the ANAH dataset. It is fine-tuned to annotate the hallucination in LLM's responses.
@@ -14,8 +25,12 @@ You have to follow the prompt in [our paper](https://arxiv.org/abs/2405.20315) t
 The models follow the conversation format of InternLM2-chat, with the template protocol as:
 
 ```python
-dict(role='user', begin='<|im_start|>user\n', end='<|im_end|>\n'),
-dict(role='assistant', begin='<|im_start|>assistant\n', end='<|im_end|>\n'),
+dict(role='user', begin='<|im_start|>user
+', end='<|im_end|>
+'),
+dict(role='assistant', begin='<|im_start|>assistant
+', end='<|im_end|>
+'),
 ```
 
 ## 🖊️ Citation
@@ -27,4 +42,7 @@ If you find this project useful in your research, please consider citing:
   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}
-}
+}
+```
+
+Code: The source code for training and evaluating this model can be found at https://github.com/open-compass/ANAH