Improve model card: Add metadata, description and Github link

This PR improves the model card by adding missing metadata (license, library_name and pipeline tag) and a link to the Github repository. The description has been updated to clarify that this is a pretraining data filter and not a language model.

README.md

@@ -1,6 +1,13 @@
 ---
 license: mit
+library_name: fasttext
+pipeline_tag: data-filtering
+tags:
+- pretraining-data-selection
 ---
-This is the fastText pretraining data filter targeting
-the LAMBADA IT task, discussed in the main text of the Perplexity
-Correlations paper: https://arxiv.org/abs/2409.05816
+
+This fastText model is a filter for selecting high-quality pretraining data, as described in [Improving Pretraining Data Using Perplexity Correlations](https://arxiv.org/abs/2409.05816). It targets the LAMBADA IT task.
+
+The model uses perplexity correlations to identify text segments highly correlated with strong performance on downstream benchmarks. It doesn't perform text classification directly; instead, it outputs a score indicating the suitability of a text segment for pretraining.
+
+For complete usage instructions and the theoretical background, please refer to the [project's GitHub repository](https://github.com/TristanThrush/perplexity-correlations).