Improve model card: fix paper link and TIL Blog Post link, set pipeline tag to text-generation, add Github link

This PR improves the model card by:

- Fixing the empty paper link, so that it points to [It's All in The [MASK]: Simple Instruction-Tuning Enables BERT-like Masked Language Models As Generative Classifiers](https://arxiv.org/abs/2502.03793).
- Fixing the empty TIL Blog Post link, as the URL was missing
- Setting the `pipeline_tag` to `text-generation` instead of `fill-mask`
- Adding a link to the Github repository, for the mini cookbook.

README.md

@@ -1,24 +1,20 @@
 ---
-library_name: transformers
-license: apache-2.0
 language:
 - en
-widget:
- - text: "You will be given a question and options. Select the right answer.
-QUESTION: If (G, .) is a group such that (ab)^-1 = a^-1b^-1, for all a, b in G, then G is a/an
-CHOICES:
-- A: commutative semi group
-- B: abelian group
-- C: non-abelian group
-- D: None of these
-ANSWER: [unused0] [MASK]"
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - fill-mask
 - masked-lm
 - long-context
 - classification
 - modernbert
-pipeline_tag: fill-mask
+widget:
+- text: 'You will be given a question and options. Select the right answer. QUESTION:
+    If (G, .) is a group such that (ab)^-1 = a^-1b^-1, for all a, b in G, then G is
+    a/an CHOICES: - A: commutative semi group - B: abelian group - C: non-abelian
+    group - D: None of these ANSWER: [unused0] [MASK]'
 inference: false
 ---
 
@@ -39,7 +35,7 @@ ModernBERT-Instruct-Large is a lightly instruction-tuned version of [ModernBERT-
 
 Despite a very straightforward pre-training and inference pipeline, this model proves to be a very strong model in a variety of contexts, in both zero-shot and fully-finetuned settings.
 
-For more details, we recommend checking out the [TIL Blog Post](), the [mini cookbook GitHub repository](https://github.com/AnswerDotAI/ModernBERT-Instruct-mini-cookbook) or the [Technical Report](https://arxiv.org/abs/2502.03793).
+For more details, we recommend checking out the [TIL Blog Post](https://til.simonwillison.net/llms/masked-language-model-classifier), the [mini cookbook GitHub repository](https://github.com/AnswerDotAI/ModernBERT-Instruct-mini-cookbook) or the [Technical Report](https://arxiv.org/abs/2502.03793).
 
 ## Usage