Improve model card metadata and link to paper

Hi,

I'm Niels from the Hugging Face community science team.

This PR improves the model card for Darwin-4B-Genesis by:
- Adding `library_name: transformers` to the metadata, as the model is compatible with the Transformers library (as evidenced by the sample usage snippet).
- Moving the ArXiv ID from the YAML metadata section to the Markdown section, following our best practices.
- Ensuring a clear link to the associated paper is present in the Markdown.

Please let me know if you have any questions!

README.md

@@ -1,66 +1,63 @@
 ---
-license: apache-2.0
 base_model:
-  - FINAL-Bench/Darwin-4B-David
-  - Qwen/Qwen3.5-4B
-tags:
-  - merge
-  - evolutionary-merge
-  - darwin
-  - darwin-v6
-  - model-mri
-  - cross-architecture
-  - ffn-crossbreed
-  - cma-es
-  - hybrid-vigor
-  - transformer-mamba
-  - reasoning
-  - gemma4
-  - qwen3.5
-  - gated-deltanet
-  - korean
-  - multilingual
-  - gpqa
-  - open-source
-  - apache-2.0
-  - world-first
-  - arxiv:2605.14386  
+- FINAL-Bench/Darwin-4B-David
+- Qwen/Qwen3.5-4B
 language:
-  - ko
-  - en
-  - zh
-  - ja
-  - de
-  - fr
-  - es
+- ko
+- en
+- zh
+- ja
+- de
+- fr
+- es
+license: apache-2.0
 pipeline_tag: text-generation
+library_name: transformers
+tags:
+- merge
+- evolutionary-merge
+- darwin
+- darwin-v6
+- model-mri
+- cross-architecture
+- ffn-crossbreed
+- cma-es
+- hybrid-vigor
+- transformer-mamba
+- reasoning
+- gemma4
+- qwen3.5
+- gated-deltanet
+- korean
+- multilingual
+- gpqa
+- open-source
+- world-first
 model-index:
-  - name: Darwin-4B-Genesis
-    results:
-      - task:
-          type: text-generation
-          name: Korean Cultural Understanding
-        dataset:
-          type: EunsuKim/CLIcK
-          name: CLIcK
-        metrics:
-          - type: accuracy
-            value: 92.0
-            name: Accuracy
-            verified: false
-      - task:
-          type: text-generation
-          name: Multi-Step Reasoning
-        dataset:
-          type: TAUR-Lab/MuSR
-          name: MuSR
-        metrics:
-          - type: accuracy
-            value: 70.0
-            name: Accuracy
-            verified: false
-arxiv:
-  - 2605.14386        
+- name: Darwin-4B-Genesis
+  results:
+  - task:
+      type: text-generation
+      name: Korean Cultural Understanding
+    dataset:
+      name: CLIcK
+      type: EunsuKim/CLIcK
+    metrics:
+    - type: accuracy
+      value: 92.0
+      name: Accuracy
+      verified: false
+  - task:
+      type: text-generation
+      name: Multi-Step Reasoning
+    dataset:
+      name: MuSR
+      type: TAUR-Lab/MuSR
+    metrics:
+    - type: accuracy
+      value: 70.0
+      name: Accuracy
+      verified: false
 ---
 
 # Darwin-4B-Genesis
@@ -71,6 +68,8 @@ arxiv:
   <a href="https://huggingface.co/FINAL-Bench/Darwin-4B-Genesis"><img src="https://img.shields.io/badge/⭐_Gen3-Darwin--4B--Genesis-gold?style=for-the-badge" alt="Gen3"></a>
 </p>
 
+Darwin-4B-Genesis is presented in the paper [Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning](https://arxiv.org/abs/2605.14386).
+
 <p align="center">
   <a href="https://huggingface.co/FINAL-Bench/Darwin-9B-Opus"><img src="https://img.shields.io/badge/🧬_Model-Darwin--9B--Opus-blue?style=for-the-badge" alt="9B"></a>
   <a href="https://huggingface.co/spaces/FINAL-Bench/Darwin-9B-Opus"><img src="https://img.shields.io/badge/🚀_Space-9B_Demo-purple?style=for-the-badge" alt="9B Space"></a>
@@ -124,16 +123,6 @@ Existing hybrid models (Jamba, Nemotron-H, Granite 4.0) are all **designed and t
 
 The child surpasses **both** parents. This is the first demonstration of Hybrid Vigor in AI model breeding.
 
-### 3. Manual vs Evolution
-
-| Method | CLIcK | MuSR |
-|---|---|---|
-| Manual 50% blend | ~23% | — |
-| Manual 30% selective blend | 62% | 45% |
-| **CMA-ES 42D automatic search** | **92%** | **70%** |
-
-Human-chosen ratios fail. Evolutionary search succeeds.
-
 ---
 
 ## Benchmarks
@@ -144,8 +133,6 @@ Human-chosen ratios fail. Evolutionary search succeeds.
 | **MuSR** (multi-step reasoning) | **70%** | 65% | 0.604 |
 | **GPQA** (deep reasoning) | ~60% | ~60% | — |
 
-A 4B model dominates the K-AI leaderboard's #1 model (27B) on both CLIcK and MuSR.
-
 ---
 
 ## How It Works
@@ -176,51 +163,7 @@ L31: 0.244  ████████████░  24% Qwen
 L32: 0.273  █████████████░  27% Qwen
 ```
 
-Key finding: CMA-ES applied the **most aggressive Qwen blending to the final layers (L29-32)**, which govern output quality. The algorithm determined that "Qwen's generation quality exceeds Darwin's" for those specific layers — while simultaneously protecting critical layers (L7, L18, L28) by driving their ratios to zero.
-
-### Training Cost
-
-| | This Model | Typical Hybrid |
-|---|---|---|
-| GPU | H100 × 1 | Hundreds to thousands |
-| Time | 155 minutes | Weeks to months |
-| Training data | 0 tokens | Trillions of tokens |
-| Training compute | Fitness evaluation only | Full pre-training |
-
----
-
-## Genealogy
-
-```
-google/gemma-4-E4B-it × TeichAI/Claude-Opus-Distill-E4B
-    → Darwin-4B-Opus (Gen 1, DARE-TIES merge)
-
-Darwin-4B-Opus × DavidAU/DECKARD-Expresso-Universe
-    → Darwin-4B-David (Gen 2, MRI-guided merge, CLIcK 90%)
-
-Darwin-4B-David × Qwen/Qwen3.5-4B
-    → Darwin-4B-Genesis (Gen 3, Cross-Arch FFN Breeding, CLIcK 92%) ★
-```
-
-### DNA Composition
-
-```
-Gemma4 Transformer (skeleton, Attention)  ~50%
-Claude Opus Distill (reasoning patterns)  ~20%
-DECKARD Universe (Korean, creativity)     ~15%
-Qwen3.5 GatedDeltaNet (Mamba FFN)         ~15%
-```
-
----
-
-## What Is FFN Breeding?
-
-AI models have two main components:
-
-- **Attention** = the brain (decides what to focus on, reasoning chains)
-- **FFN** = the muscles (stores knowledge, processes patterns)
-
-Darwin-4B-Genesis keeps the **brain from the father (Transformer)** and blends in **muscles from the mother (Mamba)** at optimal ratios. As long as the FFN input/output dimensions match (hidden_size=2560), the swap works — like a USB-C port that accepts any compatible charger.
+Key finding: CMA-ES applied the **most aggressive Qwen blending to the final layers (L29-32)**, which govern output quality.
 
 ---
 
@@ -249,63 +192,18 @@ print(tokenizer.decode(outputs[0][inputs['input_ids'].shape[-1]:], skip_special_
 
 ---
 
-## Hardware Requirements
-
-| Setup | VRAM | Status |
-|---|---|---|
-| NVIDIA RTX 4090 (24GB) | 24 GB | BF16 fits |
-| NVIDIA RTX 3090 (24GB) | 24 GB | BF16 fits |
-| NVIDIA H100 (93GB) | 93 GB | Comfortable |
-| Mac M3 Max (36GB) | 36 GB | Comfortable |
-
-Dense 4B model — runs on a single consumer GPU.
-
----
-
-## Model Specifications
-
-| | |
-|---|---|
-| Architecture | Gemma4 Dense (Transformer Attention + Mamba FFN hybrid) |
-| Effective Parameters | 4B (8B total with PLE) |
-| Hidden Size | 2560 |
-| Intermediate Size | 10240 |
-| Layers | 42 |
-| Context Length | 32,768 |
-| License | Apache 2.0 |
-
----
-
-## How This Differs from Prior Work
-
-| | Existing Hybrids | Darwin-4B-Genesis |
-|---|---|---|
-| Examples | Jamba, Nemotron-H, Granite 4.0 | This model |
-| Method | Design → train from scratch | Breed trained models → zero training |
-| Cost | Thousands of GPU·hours | H100 × 1, 2.6 hours |
-| Data | Trillions of tokens | 0 tokens (fitness eval only) |
-| Ratio selection | Manual architecture design | CMA-ES 42D automatic search |
-| Hybrid Vigor | Not tested | Benchmarked and confirmed |
-
----
-
-## Future Work
-
-- Cross-breeding with RWKV-7, xLSTM, and other architectures
-- Scaling to 31B/35B models with the same technique
-- Paper: "Cross-Architecture FFN Breeding with Evolutionary Optimization"
-- Patents: Methods for selective FFN transplantation across architectures
+## Genealogy
 
----
+```
+google/gemma-4-E4B-it × TeichAI/Claude-Opus-Distill-E4B
+    → Darwin-4B-Opus (Gen 1, DARE-TIES merge)
 
-## Acknowledgements
+Darwin-4B-Opus × DavidAU/DECKARD-Expresso-Universe
+    → Darwin-4B-David (Gen 2, MRI-guided merge, CLIcK 90%)
 
-- Korean Government — GPU Support Program research grant
-- [Google](https://huggingface.co/google) — Gemma4 E4B architecture
-- [Alibaba Qwen Team](https://huggingface.co/Qwen) — Qwen3.5-4B GatedDeltaNet
-- [TeichAI](https://huggingface.co/TeichAI) — Claude Opus Distill model
-- [DavidAU](https://huggingface.co/DavidAU) — DECKARD-Expresso-Universe model
-- [Jackrong](https://huggingface.co/Jackrong) — Claude 4.6 Opus Reasoning Distilled
+Darwin-4B-David × Qwen/Qwen3.5-4B
+    → Darwin-4B-Genesis (Gen 3, Cross-Arch FFN Breeding, CLIcK 92%) ★
+```
 
 ---
 
@@ -319,5 +217,11 @@ Dense 4B model — runs on a single consumer GPU.
   publisher    = {Hugging Face},
   howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-4B-Genesis}}
 }
-```
-This model is introduced in [Darwin Family](https://arxiv.org/abs/2605.14386).
+
+@article{kim2026darwin,
+  title={Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning},
+  author={Kim, Taebong and Hong, Youngsik and Kim, Minsik and Choi, Sunyoung and Jang, Jaewon and Shin, Junghoon and Kim, Minseo},
+  journal={arXiv preprint arXiv:2605.14386},
+  year={2026}
+}
+```