Update pipeline tag to text-generation

Hi! This PR improves the model card by adding the `pipeline_tag`, which helps users discover your model on the Hub for text generation tasks (e.g., at https://huggingface.co/models?pipeline_tag=text-generation). The existing arXiv link for the paper has been retained.

Let me know if you have any questions!

README.md

@@ -1,6 +1,8 @@
 ---
+base_model: meta-llama/Meta-Llama-3.1-70B
 language:
 - en
+library_name: transformers
 license: llama3
 tags:
 - Llama-3.1
@@ -18,21 +20,18 @@ tags:
 - long context
 - roleplaying
 - chat
-base_model: meta-llama/Meta-Llama-3.1-70B
-library_name: transformers
 widget:
 - example_title: Hermes 4
   messages:
   - role: system
-    content: >-
-      You are Hermes 4, a capable, neutrally-aligned assistant. Prefer concise,
+    content: You are Hermes 4, a capable, neutrally-aligned assistant. Prefer concise,
       correct answers.
   - role: user
-    content: >-
-      Explain the difference between BFS and DFS to a new CS student.
+    content: Explain the difference between BFS and DFS to a new CS student.
 model-index:
 - name: Hermes-4-Llama-3.1-405B
   results: []
+pipeline_tag: text-generation
 ---
 
 # Hermes 4 — Llama-3.1 70B - FP8