Improve model card: Add pipeline tag, base model, code, and project page links

This PR improves the model card by:

- Adding the `pipeline_tag: text-generation` to the metadata for better discoverability on the Hugging Face Hub.
- Updating the `base_model` in the metadata to `Qwen-Qwen2.5-1.5B-Instruct` as indicated in the merge details.
- Adding a link to the associated GitHub repository: https://github.com/rohitgandikota/erasing-llm
- Adding a link to the project page: https://elm.baulab.info
- Restructuring the paper link to be more prominent at the top of the model card.

README.md

@@ -1,14 +1,20 @@
 ---
-base_model: []
+base_model:
+- Qwen-Qwen2.5-1.5B-Instruct
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+pipeline_tag: text-generation
 ---
+
 # qwen25-instruct-with-gsm8k-reasoning
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit) as described in the paper "Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic".
+
+-   Paper: [Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic](https://arxiv.org/abs/2509.01363)
+-   Code: [https://github.com/rohitgandikota/erasing-llm](https://github.com/rohitgandikota/erasing-llm)
+-   Project page: [https://elm.baulab.info](https://elm.baulab.info)
 
 ## Merge Details
 ### Merge Method
@@ -36,6 +42,4 @@ models:
       weight: -1.0
 merge_method: task_arithmetic
 dtype: bfloat16
-```
-
-paper : https://arxiv.org/abs/2509.01363 
+```