Improve model card: Add pipeline tag, correct base model, and add code/project links

This PR significantly improves the model card for Hermes 4 14B by:

1. **Adding `pipeline_tag: text-generation` to the metadata**: This correctly categorizes the model as a generative language model, improving its discoverability on the Hugging Face Hub (e.g., https://huggingface.co/models?pipeline_tag=text-generation).
2. **Correcting `base_model` in metadata**: Updated `base_model` from `NousResearch/Hermes-4-14B` to `Qwen-3-14B` to accurately reflect that the model is based on Qwen 3 14B, as stated in its description.
3. **Enhancing paper link**: Added the official Hugging Face Papers link for the "Hermes 4 Technical Report" alongside the existing arXiv link, offering users more options to access the paper.
4. **Adding GitHub Repository link**: Included a new "Code" section with a link to the official GitHub repository for Hermes 4 (`https://github.com/NousResearch/Hermes-4`), providing easy access to the source code.
5. **Adding dedicated Project Page section**: Elevated the link to the Hermes 4 collection on Hugging Face to its own "Project Page" section for better visibility and navigation, and removed the redundant link from the "Quantized / Smaller Variants" section.

No changes were made to the existing `transformers` usage example as it is correct and valid.

README.md

@@ -1,7 +1,11 @@
 ---
+base_model:
+- Qwen-3-14B
 language:
 - en
+library_name: transformers
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - Qwen-3-14B
 - instruct
@@ -18,9 +22,6 @@ tags:
 - long context
 - roleplaying
 - chat
-base_model:
-- NousResearch/Hermes-4-14B
-library_name: transformers
 widget:
 - example_title: Hermes 4
   messages:
@@ -42,12 +43,19 @@ model-index:
 
 Hermes 4 14B is a frontier, hybrid-mode **reasoning** model based on Qwen 3 14B by Nous Research that is aligned to **you**.
 
-Read the Hermes 4 technical report here: <a href="https://arxiv.org/abs/2508.18255">Hermes 4 Technical Report</a>
+Read the Hermes 4 technical report here: [Hermes 4 Technical Report (arXiv)](https://arxiv.org/abs/2508.18255) | [Hermes 4 Technical Report (Hugging Face Papers)](https://huggingface.co/papers/2508.18255)
 
 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.
 
+## Project Page
+
+Explore the full Hermes 4 collection on the Hugging Face Hub: [Hermes 4 Collection](https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728)
+
+## Code
+
+The official GitHub repository for Hermes 4 can be found here: [https://github.com/NousResearch/Hermes-4](https://github.com/NousResearch/Hermes-4)
 
 ## What’s new vs Hermes 3
 
@@ -202,9 +210,6 @@ GGUF (Courtesy of LM Studio team!):
 
 Hermes 4 is also available in larger sizes (e.g., 70B, 405B) with similar prompt formats.
 
-See the Hermes 4 collection to explore them all:
-https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728
-
 # How to cite
 
 ```bibtex