Improve model card: Add library name

This PR adds the `library_name: transformers` field to the model card metadata. The provided code examples clearly demonstrate the model's compatibility with the Hugging Face `transformers` library. This addition enhances the model card's clarity and improves discoverability for users seeking models compatible with this popular library.

README.md

@@ -1,21 +1,32 @@
 ---
-license: mit
-license_link: https://huggingface.co/microsoft/Phi-3-small-128k-instruct/resolve/main/LICENSE
-
 language:
 - multilingual
+license: mit
+license_link: https://huggingface.co/microsoft/Phi-3-small-128k-instruct/resolve/main/LICENSE
 pipeline_tag: text-generation
 tags:
 - nlp
 - code
+library_name: transformers
 inference:
   parameters:
     temperature: 0.7
 widget:
-  - messages:
-      - role: user
-        content: Can you provide ways to eat combinations of bananas and dragonfruits?
+- messages:
+  - role: user
+    content: Can you provide ways to eat combinations of bananas and dragonfruits?
 ---
+
+# LongRoPE2: Near-Lossless LLM Context Window Scaling
+
+The model was presented in the paper [LongRoPE2: Near-Lossless LLM Context Window Scaling](https://hf.co/papers/2502.20082).
+
+# Paper abstract
+
+The abstract of the paper is the following:
+
+LongRoPE2 is a novel approach that extends the effective context window of pre-trained large language models (LLMs) to the target length, while preserving the performance on the original shorter context window. This is achieved by three contributions: (1) a hypothesis that insufficient training in higher RoPE dimensions contributes to the persistent out-of-distribution (OOD) issues observed in existing methods; (2) an effective RoPE rescaling algorithm that adopts evolutionary search guided by "needle-driven" perplexity to address the insufficient training problem; (3) a mixed context window training approach that fine-tunes model weights to adopt rescaled RoPE for long-context sequences while preserving the short-context performance with the original RoPE. Extensive experiments on LLaMA3-8B and Phi3-mini-3.8B across various benchmarks validate the hypothesis and demonstrate the effectiveness of LongRoPE2. Remarkably, LongRoPE2 extends LLaMA3-8B to achieve a 128K effective context length while retaining over 98.5% of short-context performance, using only 10B tokens -- 80x fewer than Meta's approach, which fails to reach the target effective context length. Code will be available at https://github.com/microsoft/LongRoPE.
+
 🎉 **Phi-3.5**: [[mini-instruct]](https://huggingface.co/microsoft/Phi-3.5-mini-instruct); [[MoE-instruct]](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct) ; [[vision-instruct]](https://huggingface.co/microsoft/Phi-3.5-vision-instruct)
 
 ## Model Summary
@@ -277,4 +288,4 @@ The model is licensed under the [MIT license](https://huggingface.co/microsoft/P
 
 ## Trademarks
 
-This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
+This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.