Add pipeline tag, library name, link to paper and Github repository

This PR adds the `text-generation` pipeline tag and `library_name: transformers` to the model card to facilitate discoverability and usability.
It also adds a link to the Github repository.
The citation section is updated with the correct Arxiv info.

README.md

@@ -1,10 +1,13 @@
 ---
-license: apache-2.0
 datasets:
 - BAAI/Infinity-Instruct
 language:
 - en
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
 ---
+
 # Infinity Instruct
 
 <p align="center">
@@ -12,7 +15,7 @@ language:
 </p>
 <p align="center">
 <em>Beijing Academy of Artificial Intelligence (BAAI)</em><br/>
-<em>[Paper][Code][🤗] (would be released soon)</em>
+<em>[Paper](https://huggingface.co/papers/2506.11116)[Code](https://github.com/BAAI/Infinity-Instruct)[\ud83e\udd17] (would be released soon)</em>
 </p>
 
 Infinity-Instruct-7M-Gen-Mistral-7B is an opensource supervised instruction tuning model without reinforcement learning from human feedback (RLHF). This model is just finetuned on [Infinity-Instruct-7M and Infinity-Instruct-Gen](https://huggingface.co/datasets/BAAI/Infinity-Instruct) and showing favorable results on AlpacaEval 2.0 compared to Mixtral 8x22B v0.1, Gemini Pro, and GPT-4.
@@ -74,7 +77,7 @@ Thanks to [FlagScale](https://github.com/FlagOpen/FlagScale), we could concatena
 
 ## **How to use**
 
-Infinity-Instruct-7M-Gen-Mistral-7B adopt the same chat template of [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B):
+Infinity-Instruct-7M-Gen-Mistral-7B adopt the same chat template of [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B):\
 
 ```bash
 <|im_start|>system
@@ -144,13 +147,13 @@ The resources, including code, data, and model weights, associated with this pro
 ## 
 
 ## **Citation**
-Our paper, detailing the development and features of the **Infinity Instruct** dataset and finetuned models, will be released soon on arXiv. Stay tuned!
+Our paper, detailing the development and features of the **Infinity Instruct** dataset and finetuned models, has been released on arXiv:
 
 ```
 @article{InfinityInstruct2024,
-  title={Infinity Instruct},
+  title={Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models},
   author={Beijing Academy of Artificial Intelligence (BAAI)},
-  journal={arXiv preprint arXiv:2406.XXXX},
+  journal={arXiv preprint arXiv:2506.11116},
   year={2024}
 }
 ```