Improve model card: Add pipeline tag, paper, project, and code links, and abstract

This PR improves the model card for Hermes 4 by:

* Adding the `pipeline_tag: text-generation` metadata, ensuring the model appears correctly in relevant searches on the Hub (https://huggingface.co/models?pipeline_tag=text-generation).
* Adding a prominent link to the Hugging Face Paper page: https://huggingface.co/papers/2508.18255.
* Adding a prominent link to the GitHub repository: https://github.com/NousResearch/Hermes-4.
* Improving the discoverability of the project page by adding a prominent link at the top: https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728.
* Including a dedicated "Abstract (from Paper)" section with the paper's abstract for a quick overview.

README.md

@@ -1,7 +1,11 @@
 ---
+base_model:
+- NousResearch/Hermes-4-14B
 language:
 - en
+library_name: transformers
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - Qwen-3-14B
 - instruct
@@ -18,15 +22,11 @@ tags:
 - long context
 - roleplaying
 - chat
-base_model:
-- NousResearch/Hermes-4-14B
-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.
@@ -34,10 +34,18 @@ model-index:
 - name: Hermes-4-Qwen-3-14B
   results: []
 ---
+
 # Hermes 4 — Qwen 3 14B
 
+Presented in [Hermes 4 Technical Report](https://huggingface.co/papers/2508.18255).
+**Project Page**: [Hermes 4 Collection](https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728)
+**Code**: [GitHub Repository](https://github.com/NousResearch/Hermes-4)
+
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/roT9o5bMYBtQziRMlaSDf.jpeg)
 
+## Abstract (from Paper)
+We present Hermes 4, a family of hybrid reasoning models that combine structured, multi-turn reasoning with broad instruction-following ability. We describe the challenges encountered during data curation, synthesis, training, and evaluation, and outline the solutions employed to address these challenges at scale. We comprehensively evaluate across mathematical reasoning, coding, knowledge, comprehension, and alignment benchmarks, and we report both quantitative performance and qualitative behavioral analysis. To support open research, all model weights are published publicly at this https URL
+
 ## Model Description
 
 Hermes 4 14B is a frontier, hybrid-mode **reasoning** model based on Qwen 3 14B by Nous Research that is aligned to **you**.
@@ -51,11 +59,11 @@ Training highlights include a newly synthesized post-training corpus emphasizing
 
 ## What’s new vs Hermes 3
 
-- **Post-training corpus**: Massively increased dataset size from 1M samples and 1.2B tokens to **~5M samples / ~60B tokens** blended across reasoning and non-reasoning data.
-- **Hybrid reasoning mode** with explicit `<think>…</think>` segments when the model decides to deliberate, and options to make your responses faster when you want.
-- **Reasoning** that is top quality, expressive, improves math, code, STEM, logic, and even creative writing and subjective responses.
-- **Schema adherence & structured outputs**: trained to produce valid JSON for given schemas and to repair malformed objects.
-- **Much easier to steer and align**: extreme improvements on steerability, especially on reduced refusal rates.
+-   **Post-training corpus**: Massively increased dataset size from 1M samples and 1.2B tokens to **~5M samples / ~60B tokens** blended across reasoning and non-reasoning data.
+-   **Hybrid reasoning mode** with explicit `<think>…</think>` segments when the model decides to deliberate, and options to make your responses faster when you want.
+-   **Reasoning** that is top quality, expressive, improves math, code, STEM, logic, and even creative writing and subjective responses.
+-   **Schema adherence & structured outputs**: trained to produce valid JSON for given schemas and to repair malformed objects.
+-   **Much easier to steer and align**: extreme improvements on steerability, especially on reduced refusal rates.
 
 ## Our Mission: Frontier Capabilities Aligned to You
 
@@ -127,8 +135,8 @@ Note that you may also simply place tool definitions into the "tools:" field of
 
 The model will then generate tool calls within `<tool_call> {tool_call} </tool_call>` tags, for easy parsing. The tool_call tags are also added tokens, so it makes it easy to parse while streaming! There are also automatic tool parsers built-in to VLLM and SGLang for Hermes, just set the tool parser in VLLM to `hermes` and in SGLang to `qwen25`.
 ## Inference Notes
-- **Sampling defaults that work well:** `temperature=0.6, top_p=0.95, top_k=20`.
-- **Template:** Use the ChatML chat format for Hermes 4 14B as shown above, or set `add_generation_prompt=True` when using `tokenizer.apply_chat_template(...)`.
+-   **Sampling defaults that work well:** `temperature=0.6, top_p=0.95, top_k=20`.
+-   **Template:** Use the ChatML chat format for Hermes 4 14B as shown above, or set `add_generation_prompt=True` when using `tokenizer.apply_chat_template(...)`.
 ### Transformers example
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -143,6 +151,7 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 messages = [
     {"role":"system","content":"You are Hermes 4. Be concise."},
+
     {"role":"user","content":"Summarize CRISPR in 3 sentences."}
 ]
 inputs = tokenizer.apply_chat_template(