Add library_name, pipeline tag and paper link

This PR adds the `library_name` to the model card, ensuring the "how to use" button is shown correctly. It also adds the pipeline tag, ensuring that it can be found at https://huggingface.co/models?pipeline_tag=text-generation. It also includes a link to the paper.

README.md

@@ -6,18 +6,21 @@ tags:
 - MiniCPM
 - ModelBest
 - THUNLP
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
-
 <div align="center">
 <h1>
   MiniCPM
 </h1>
 </div>
 
+This repository contains the model of the paper [MiniCPM4: Ultra-Efficient LLMs on End Devices](https://huggingface.co/papers/2506.07900).
+
 <p align="center">
 <a href="https://shengdinghu.notion.site/MiniCPM-c805a17c5c8046398914e47f0542095a?pvs=4" target="_blank">MiniCPM 技术报告</a><a href="https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20?pvs=4" target="_blank"> Technical Report</a> |
-<a href="https://github.com/OpenBMB/OmniLMM/" target="_blank">OmniLMM 多模态模型 Multi-modal Model</a> |
+<a href="https://github.com/OpenBMB/OmniLMM/\" target="_blank">OmniLMM 多模态模型 Multi-modal Model</a> |
 <a href="https://luca.cn/" target="_blank">CPM-C 千亿模型试用 ~100B Model Trial </a> 
 </p>
 
@@ -36,7 +39,7 @@ MiniCPM 是面壁与清华大学自然语言处理实验室共同开源的系列
 - 基于MLC-LLM、LLMFarm开发的MiniCPM手机端程序，**文本及多模态模型均可在手机端进行推理。**
 
 
-MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings.
+MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings。
 
 - MiniCPM has very close performance compared with Mistral-7B on open-sourced general benchmarks with better ability on Chinese, Mathmetics and Coding after SFT. The overall performance exceeds Llama2-13B, MPT-30B, Falcon-40B, etc.
 - After DPO, MiniCPM outperforms Llama2-70B-Chat, Vicuna-33B, Mistral-7B-Instruct-v0.1, Zephyr-7B-alpha, etc. on MTBench.
@@ -148,4 +151,4 @@ print(responds)
  booktitle={OpenBMB Blog},
  year={2024}
 }
-```
+```