Improve model card: paper link, project link, remove misleading library_name for GGUF

This PR improves the model card for `openbmb/BitCPM4-1B-GGUF` by:

- Updating the paper link to point to the official Hugging Face paper page: https://huggingface.co/papers/2506.07900.
- Adding a link to the project's Hugging Face collection (project page) for better overview: https://huggingface.co/collections/openbmb/minicpm4-6841ab29d180257e940baa9b.
- Removing the misleading `library_name: transformers` metadata, as this specific GGUF model is intended for use with `llama.cpp` (as demonstrated in the usage example) and not the `transformers` library for direct inference.
- Adding a descriptive main title to the model card for clarity.
- Updating the bibtex entry to include the URL to the paper.

README.md

@@ -1,25 +1,31 @@
 ---
-license: apache-2.0
 language:
 - zh
 - en
+license: apache-2.0
 pipeline_tag: text-generation
-library_name: transformers
 ---
+
 <div align="center">
-<img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img> 
+<img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img>
 </div>
 
+# MiniCPM4: Ultra-Efficient LLMs on End Devices - BitCPM4-1B-GGUF
+
+This repository contains the `BitCPM4-1B-GGUF` model, part of the MiniCPM4 series, as presented in [MiniCPM4: Ultra-Efficient LLMs on End Devices](https://huggingface.co/papers/2506.07900).
+
 <p align="center">
 <a href="https://github.com/OpenBMB/MiniCPM/" target="_blank">GitHub Repo</a> |
-<a href="https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf" target="_blank">Technical Report</a> 
+<a href="https://huggingface.co/papers/2506.07900" target="_blank">Paper</a> |
+<a href="https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf" target="_blank">Technical Report</a> |
+<a href="https://huggingface.co/collections/openbmb/minicpm4-6841ab29d180257e940baa9b" target="_blank">Project Page</a>
 </p>
 <p align="center">
 👋 Join us on <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
 </p>
 
 ## What's New
-- [2025.06.06] **MiniCPM4** series are released! This model achieves ultimate efficiency improvements while maintaining optimal performance at the same scale! It can achieve over 5x generation acceleration on typical end-side chips! You can find technical report [here](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf).🔥🔥🔥
+- [2025.06.06] **MiniCPM4** series are released! This model achieves ultimate efficiency improvements while maintaining optimal performance at the same scale! It can achieve over 5x generation acceleration on typical end-side chips! You can find technical report [here](https://huggingface.co/papers/2506.07900).🔥🔥🔥
 
 ## MiniCPM4 Series
 MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.
@@ -55,21 +61,21 @@ BitCPM4's performance is comparable with other full-precision models in same mod
 ![Benchmark of BitCPM](https://raw.githubusercontent.com/OpenBMB/MiniCPM/refs/heads/main/assets/minicpm4/bitcpm4-benchmark.png)
 
 ## Statement
-- As a language model, MiniCPM generates content by learning from a vast amount of text. 
-- However, it does not possess the ability to comprehend or express personal opinions or value judgments. 
-- Any content generated by MiniCPM does not represent the viewpoints or positions of the model developers. 
+- As a language model, MiniCPM generates content by learning from a vast amount of text.
+- However, it does not possess the ability to comprehend or express personal opinions or value judgments.
+- Any content generated by MiniCPM does not represent the viewpoints or positions of the model developers.
 - Therefore, when using content generated by MiniCPM, users should take full responsibility for evaluating and verifying it on their own.
 
 ## LICENSE
-- This repository and MiniCPM models are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License. 
+- This repository and MiniCPM models are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
 
 ## Citation
-- Please cite our [paper](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf) if you find our work valuable.
+- Please cite our [paper](https://huggingface.co/papers/2506.07900) if you find our work valuable.
 
 ```bibtex
 @article{minicpm4,
   title={{MiniCPM4}: Ultra-Efficient LLMs on End Devices},
   author={MiniCPM Team},
-  year={2025}
-}
-```
+  year={2025},
+  url={https://huggingface.co/papers/2506.07900},
+}