Improve model card: add paper details, update license, and add library tag

This PR significantly enhances the model card for the `Single-Pass Scanner` by:

- Updating the main heading to the official paper title, "[Single-Pass Document Scanning for Question Answering](https://huggingface.co/papers/2504.03101)".
- Adding a direct link to the paper and its abstract for comprehensive context.
- Explicitly linking to the official [GitHub repository](https://github.com/MambaRetriever/MambaRetriever) for code, setup, and evaluation details.
- Including a link to the [Hugging Face Datasets](https://huggingface.co/datasets/MambaRetriever/MambaRetriever) used for training and evaluation.
- Correcting the `license` metadata from `apache-2.0` to `mit`, aligning with the project's code license as stated in the GitHub README.
- Adding `library_name: transformers` to the metadata for better discoverability and compatibility on the Hub.
- Removing the extraneous "File information" section.

These changes aim to make the model card more informative and user-friendly.

README.md

@@ -1,21 +1,27 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - state-spaces/mamba2-1.3b
+language:
+- en
+license: mit
 pipeline_tag: question-answering
+library_name: transformers
 ---
 
+# Single-Pass Document Scanning for Question Answering
+
+This repository contains the model checkpoint for [Single-Pass Document Scanning for Question Answering](https://huggingface.co/papers/2504.03101), presented in the paper of the same name.
 
-# Single-Pass Scanner
+The Single-Pass Scanner addresses the challenge of handling extremely large documents for question answering by processing the entire text in linear time, preserving global coherence while identifying the most relevant sentences for a given query. Built upon the Mamba architecture, it offers a computationally efficient solution for QA over massive text.
 
-This repository contains model checkpoint for [Single-Pass Scanner](https://github.com/MambaRetriever/MambaRetriever)
+## Abstract
+Handling extremely large documents for question answering is challenging: chunk-based embedding methods often lose track of important global context, while full-context transformers can be prohibitively expensive for hundreds of thousands of tokens. We propose a single-pass document scanning approach that processes the entire text in linear time, preserving global coherence while deciding which sentences are most relevant to the query. On 41 QA benchmarks, our single-pass scanner consistently outperforms chunk-based embedding methods and competes with large language models at a fraction of the computational cost. By conditioning on the entire preceding context without chunk breaks, the method preserves global coherence, which is especially important for long documents. Overall, single-pass document scanning offers a simple solution for question answering over massive text.
 
-The model architecture is built upon [mamba](https://github.com/state-spaces/mamba), and is trained from [mamba2-1.3b](https://huggingface.co/state-spaces/mamba2-1.3b)
+For the official code, setup instructions, and detailed evaluation, please refer to the [Single-Pass Scanner GitHub repository](https://github.com/MambaRetriever/MambaRetriever). The training and evaluation datasets are available at [Hugging Face Datasets](https://huggingface.co/datasets/MambaRetriever/MambaRetriever).
 
+The model architecture is built upon [mamba](https://github.com/state-spaces/mamba), and is trained from [mamba2-1.3b](https://huggingface.co/state-spaces/mamba2-1.3b).
 
-# Usage
+## Usage
 
 We highly recommend creating a new conda environment first:
 ```