Improve model card: add pipeline tag, project page, and fix sample usage model_id

This PR improves the model card for Hermes 4 by:

* Adding the `pipeline_tag: text-generation` to the metadata for better discoverability and categorization on the Hugging Face Hub.
* Adding an explicit "Project Page" link near the top of the model card content, linking to the Hermes 4 collection.
* Correcting the `model_id` in the "Transformers example" code snippet from `NousResearch/Hermes-4-14B` to `NousResearch/Hermes-4-14B-FP8` to accurately reflect this model's specific FP8 version.

README.md

@@ -1,6 +1,8 @@
 ---
+base_model: Qwen/Qwen3-14B
 language:
 - en
+library_name: transformers
 license: apache-2.0
 tags:
 - Qwen-3-14B
@@ -18,21 +20,18 @@ tags:
 - long context
 - roleplaying
 - chat
-base_model: Qwen/Qwen3-14B
-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-Qwen-3-14B
   results: []
+pipeline_tag: text-generation
 ---
 
 # Hermes 4 — Qwen-3 14B
@@ -45,6 +44,8 @@ Hermes 4 14B is a frontier, hybrid-mode **reasoning** model based on Qwen 3 14B
 
 Read the Hermes 4 technical report here: <a href="https://arxiv.org/abs/2508.18255">Hermes 4 Technical Report</a>
 
+Project Page: https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728
+
 Chat with Hermes in Nous Chat: https://chat.nousresearch.com
 
 Training highlights include a newly synthesized post-training corpus emphasizing verified reasoning traces, massive improvements in math, code, STEM, logic, creativity, and format-faithful outputs, while preserving general assistant quality and broadly neutral alignment.
@@ -142,7 +143,7 @@ The model will then generate tool calls within `<tool_call> {tool_call} </tool_c
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "NousResearch/Hermes-4-14B"
+model_id = "NousResearch/Hermes-4-14B-FP8" # Corrected model_id
 
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(