Update README.md

README.md

@@ -1,3 +1,455 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model:
+  - Qwen/Qwen3.5-35B-A3B
+  - Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
+tags:
+  - merge
+  - evolutionary-merge
+  - darwin
+  - darwin-v5
+  - model-mri
+  - reasoning
+  - advanced-reasoning
+  - chain-of-thought
+  - thinking
+  - qwen3.5
+  - qwen
+  - moe
+  - mixture-of-experts
+  - claude-opus
+  - distillation
+  - multimodal
+  - vision-language
+  - multilingual
+  - 201-languages
+  - gpqa
+  - benchmark
+  - open-source
+  - apache-2.0
+  - natural-selection
+  - layer-wise-merge
+  - coding-agent
+  - tool-calling
+  - long-context
+  - 262k-context
+language:
+  - en
+  - zh
+  - ko
+  - ja
+  - de
+  - fr
+  - es
+  - ru
+  - ar
+  - multilingual
+pipeline_tag: text-generation
+library_name: transformers
+model-index:
+  - name: Darwin-35B-A3B-Opus
+    results:
+      - task:
+          type: text-generation
+          name: Graduate-Level Reasoning
+        dataset:
+          type: Idavidrein/gpqa
+          name: GPQA Diamond
+          config: gpqa_diamond
+          split: train
+        metrics:
+          - type: accuracy
+            value: 90.0
+            name: Accuracy
+            verified: false
+      - task:
+          type: text-generation
+          name: Multilingual Knowledge
+        dataset:
+          type: openai/MMMLU
+          name: MMMLU
+        metrics:
+          - type: accuracy
+            value: 85.0
+            name: Accuracy
+            verified: false
+---
+
+# Darwin-35B-A3B-Opus
+
+<p align="center">
+  <em>"The child surpassed both parents — that is evolution."</em>
+</p>
+
+<!-- SEO: Structured Summary for Search Engines & AI Answer Engines -->
+<!-- 
+Darwin-35B-A3B-Opus is a 35B parameter Mixture-of-Experts (MoE) language model with 3B active parameters, 
+created by VIDRAFT using the Darwin V5 evolutionary merge engine with Model MRI integration.
+It achieves 90.0% on GPQA Diamond (vs Father Qwen3.5-35B-A3B at 84.2%) and 85.0% on MMMLU,
+while preserving multimodal capabilities (image/video), 201 language support, and 262K context length.
+Licensed under Apache 2.0.
+-->
+
+> **TL;DR**: 35B MoE (3B active) | **GPQA Diamond 90.0%** (beats Father 84.2% & Mother 85.0%) | **MMMLU 85.0%** | Multimodal ✅ | 201 Languages | 262K Context | 147.8 tok/s | Apache 2.0
+>
+> `#Darwin` `#EvolutionaryMerge` `#ModelMRI` `#Qwen3.5` `#MoE` `#Reasoning` `#GPQA90` `#Multimodal` `#OpenSource` `#Apache2` `#DarwinV5` `#VIDRAFT`
+
+---
+
+## Why Darwin? — The Child That Surpassed Both Parents
+
+The fundamental question of AI model merging: **If parent models already exist, why crossbreed?**
+
+This model is the answer.
+
+### Benchmark Results
+
+**GPQA Diamond (198 Questions, Graduate-Level Reasoning)**
+
+| Model | Accuracy | Multimodal | Benchmark Published |
+|---|---|---|---|
+| 🧬 **Darwin-35B-A3B-Opus (Child)** | **90.0%** | ✅ Image/Video | ✅ Fully Open |
+| 👩 Mother — Jackrong Claude 4.6 Opus Distilled | 85.0% | ❌ Text-only | ❌ Not Published |
+| 👨 Father — Qwen3.5-35B-A3B (Official) | 84.2% | ✅ Image/Video | ✅ Official |
+
+> *Evaluation: SGLang, context 32768, temperature 0, greedy decoding, official GPQA prompt format ("ANSWER: LETTER")*
+
+**MMMLU (Multilingual Knowledge, 29 Languages)**
+
+| Model | Accuracy |
+|---|---|
+| 🧬 **Darwin-35B-A3B-Opus (Child)** | **85.0%** |
+| 👨 Father — Qwen3.5-35B-A3B (Official) | 85.2% |
+
+> *Darwin maintains Father-level multilingual knowledge while gaining superior reasoning.*
+
+**The child surpassed both parents in reasoning, and matched the Father in multilingual knowledge.**
+
+- GPQA vs Father: **+6.9% relative improvement** ((90.0−84.2)/84.2)
+- GPQA vs Mother: **+5.9% relative improvement** ((90.0−85.0)/85.0)
+- MMMLU: **85.0%** — Father-level (85.2%) multilingual knowledge preserved
+
+### Why Not Just Use the Mother?
+
+| | Mother (Claude Distilled) | Darwin (Child) |
+|---|---|---|
+| Reasoning | Strong (85.0%) | **Stronger (90.0%)** |
+| Image/Video | ❌ Lost (text-only fine-tune) | ✅ Inherited from Father |
+| 201 Languages | ❌ Potentially degraded | ✅ Inherited from Father |
+| 262K Context | Unverified | ✅ Father's architecture preserved |
+| Benchmark Transparency | ❌ No scores published | ✅ Fully open |
+
+### Why Not Just Use the Father?
+
+The Father (Qwen3.5-35B-A3B) excels in versatility but scores 84.2% on hard reasoning. Darwin **pushes reasoning to 90.0%** while maintaining Father-level multilingual knowledge (MMMLU 85.0% vs 85.2%) and all general capabilities.
+
+**Conclusion: The only model that surpasses the Mother's reasoning, preserves the Father's multilingual knowledge, and retains full multimodal capabilities.**
+
+---
+
+## Model Overview
+
+**Darwin-35B-A3B-Opus** is a next-generation reasoning-enhanced language model created by VIDRAFT's **Darwin V5** evolution engine.
+
+Darwin V5 combines two innovations:
+1. **Evolutionary Merge** — Applies natural selection to automatically find optimal weight combinations
+2. **Model MRI Integration** — CT-scans parent models layer by layer before merging, guiding evolution with structural insight
+
+If conventional merging is "mixing recipes blindfolded," Darwin V5 is **"precision surgery with X-ray guidance."**
+
+---
+
+## Parent Models
+
+| Role | Model | Strengths |
+|---|---|---|
+| 👨 Father | [Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B) | General knowledge, multimodal (image/video), coding, agents, 201 languages, 262K context |
+| 👩 Mother | [Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled](https://huggingface.co/Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled) | Claude 4.6 Opus CoT distillation, structured step-by-step reasoning, coding agent compatibility |
+
+---
+
+## Darwin V5 — Beyond Simple Merge
+
+### Limitations of Conventional Merging
+
+Traditional model merging relies on humans setting hyperparameters like ratio and density **by intuition**. Set ratio=0.5, density=0.9, run once, and hope for the best. The result depends on luck, and applying the same ratio uniformly across billions of parameters ignores each layer's unique role.
+
+### Darwin V4's Advance
+
+Darwin V4 solved this with **evolutionary algorithms** — automatically searching hundreds of parameter combinations and selecting survivors by real benchmark scores. But V4 was still **blind evolution**: it didn't know what each layer does.
+
+### Darwin V5: Model MRI Opens the Eyes
+
+V5 integrates **Model MRI** (neural anatomy analyzer) to give evolution "sight":
+
+```
+[Phase 0] Model MRI — CT-scan both parents layer by layer
+    ↓  "Father's layers 15-25 concentrate multilingual knowledge"
+    ↓  "Mother's layers 30-40 concentrate reasoning patterns"
+    ↓
+[Phase 1] MRI-Guided Evolution — Start from scan-informed initial genome
+    ↓  Not random, but "informed by CT results"
+    ↓
+[Phase 2] mergekit real merge + benchmark fitness selection
+    ↓  Faster convergence in MRI-narrowed search space
+    ↓
+[Phase 3] MRI Health Check — CT-scan the child model
+    ↓  Detect interference, function loss
+    ↓  Prescribe layer-specific ratio adjustments
+    ↓
+[Final] Darwin-35B-A3B-Opus
+```
+
+### V4 vs V5
+
+| | Darwin V4 | Darwin V5 |
+|---|---|---|
+| Analogy | Mixing recipes blindfolded | **Precision surgery with X-ray** |
+| Initial genome | Random | **MRI-guided** |
+| Layer control | 2 ratios (attn/ffn) | **40 layers independently** |
+| Pre-diagnosis | ❌ None | ✅ Phase 0 MRI scan |
+| Post-verification | Benchmark only | ✅ Phase 3 health check |
+| Search efficiency | Wide space | **Narrowed, guided search** |
+| Failure diagnosis | Unknown "why" | **Pinpoint which layer failed** |
+
+---
+
+### Discovered Optimal Parameters
+
+| Parameter | Value | Meaning |
+|---|---|---|
+| ratio | 0.481 | Father 52% : Mother 48% asymmetric blend |
+| density_a | 0.855 | Selected 85.5% of Father's weights |
+| density_b | 0.971 | Adopted 97.1% of Mother's weights |
+| attn | 0.168 | Only 16.8% change in attention layers |
+| ffn | 0.841 | 84.1% change in FFN layers |
+
+**Interpretation:** Attention patterns (what to focus on) are **almost entirely preserved** from the Father, while FFN layers (knowledge storage) are **largely replaced** with the Mother's reasoning patterns.
+
+Discovering attn=0.168 and ffn=0.841 — this extreme asymmetry — is **virtually impossible by human intuition**.
+
+### Evolution History
+
+- Phase 1 → Phase 2 evolution complete
+- Final real_score: **0.8405**
+- Merge time: 181.6 seconds
+- Merge commit: `109838c2`
+
+---
+
+## Inherited Capabilities
+
+### From Father (Qwen3.5-35B-A3B)
+- **Multimodal**: Image and video understanding
+- **201 Languages**: Global linguistic coverage
+- **262K Context**: Native long-context (extendable to 1M via YaRN)
+- **Gated DeltaNet + MoE**: Efficient hybrid architecture
+- **Multi-Token Prediction**: Improved inference throughput
+
+### From Mother (Claude 4.6 Opus Distilled)
+- **Structured Thinking**: Systematic step-by-step reasoning within `<think>` tags
+- **Efficient Reasoning**: "Let me analyze this request carefully: 1..2..3..." pattern
+- **Coding Agent Compatibility**: Native "developer" role support for Claude Code, OpenCode
+- **Tool Calling Stability**: Consistent performance in tool-use scenarios
+- **Autonomous Execution**: Extended autonomous operation in agentic environments
+
+---
+
+## Father's Official Benchmarks (Reference)
+
+Darwin is built on this architecture with enhanced reasoning:
+
+| Category | Benchmark | Father Official |
+|---|---|---|
+| Knowledge | MMLU-Pro | 85.3 |
+| Knowledge | MMLU-Redux | 93.3 |
+| Reasoning | GPQA Diamond | 84.2 |
+| Reasoning | HLE w/ CoT | 22.4 |
+| Math | HMMT Feb 2025 | 89.0 |
+| Coding | SWE-bench Verified | 69.2 |
+| Coding | LiveCodeBench v6 | 74.6 |
+| Agent | TAU2-Bench | 81.2 |
+| Agent | BFCL-V4 (Tool Use) | 67.3 |
+| Instruction | IFEval | 91.9 |
+| Multilingual | MMMLU | 85.2 |
+| Agentic Search | BrowseComp | 61.0 |
+
+---
+
+## Performance
+
+### Inference Speed
+
+| Metric | Value |
+|---|---|
+| **Generation Speed** | **147.8 tok/s** |
+| Environment | Single NVIDIA H100 93GB NVL, SGLang, BF16 |
+| Qwen Official API | 162.8 tok/s (Alibaba Cloud) |
+
+### Hardware Requirements
+
+| Setup | VRAM | Status |
+|---|---|---|
+| **BF16 (Full Precision)** | **65.5 GiB** | |
+| Single H100 93GB NVL | 93 GB | ✅ Comfortable |
+| Single A100 80GB | 80 GB | ⚠️ Tight |
+| Single A100 40GB | 40 GB | ❌ Insufficient |
+| **Q8 Quantized** | **~35 GiB** | |
+| Single A100 40GB | 40 GB | ✅ Possible |
+| **Q4_K_M Quantized** | **~18 GiB** | |
+| Single RTX 4090 24GB | 24 GB | ✅ Comfortable |
+| 2× RTX 4090 (tp=2) | 48 GB | ✅ BF16 possible |
+
+> As a Mixture-of-Experts model, only 3B parameters are active per token despite loading the full 35B. Quantization has minimal impact due to this sparsity.
+
+---
+
+## Model Specifications
+
+| | |
+|---|---|
+| Architecture | Qwen3.5 MoE (Gated DeltaNet + MoE) |
+| Total Parameters | 35B |
+| Active Parameters | 3B per forward pass |
+| Hidden Dimension | 2,048 |
+| Layers | 40 |
+| Layer Layout | 10 × (3 × GDN→MoE + 1 × Attention→MoE) |
+| Experts | 256 (8 routed + 1 shared active) |
+| Expert Intermediate Dim | 512 |
+| Context Length | 262,144 native (up to 1,010,000 via YaRN) |
+| Languages | 201 |
+| Multimodal | ✅ Image & Video input |
+| License | Apache 2.0 |
+| Engine | Darwin V5 (Evolutionary Merge + Model MRI) |
+| Evolution Phase | Phase 2, real_score 0.8405 |
+| Merge Commit | 109838c2 |
+
+---
+
+## Usage
+
+### SGLang (Recommended)
+
+```bash
+python -m sglang.launch_server \
+  --model-path FINAL-Bench/Darwin-35B-A3B-Opus \
+  --tp 1 \
+  --mem-fraction-static 0.90 \
+  --context-length 32768 \
+  --trust-remote-code
+```
+
+### vLLM
+
+```bash
+vllm serve FINAL-Bench/Darwin-35B-A3B-Opus \
+  --trust-remote-code \
+  --enforce-eager
+```
+
+### Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("FINAL-Bench/Darwin-35B-A3B-Opus", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    "FINAL-Bench/Darwin-35B-A3B-Opus",
+    dtype="bfloat16",
+    device_map="auto",
+    trust_remote_code=True,
+)
+```
+
+### Best Practices
+- Use **context ≥ 32K** for reasoning tasks — the model leverages extended thinking
+- For maximum reasoning quality, use **thinking mode (default)** with sufficient max_tokens (≥ 16384)
+- The model generates `<think>` blocks for internal reasoning; extract the final answer after `</think>`
+
+---
+
+## Built By
+
+| | |
+|---|---|
+| Developer | **VIDRAFT** |
+| Evolution Engine | Darwin V5 (Evolutionary Merge + Model MRI) |
+| Infrastructure | 4 × NVIDIA H100 93GB NVL GPU |
+| Merge Time | 181.6 seconds |
+| Shard Distribution | 14 shards → GPU [1, 2, 3] round-robin |
+
+---
+
+## Acknowledgements
+
+- **Korean Government** — This research was supported by the Korean Government's 'GPU Support Program' research grant
+- [Qwen Team](https://huggingface.co/Qwen) — Qwen3.5-35B-A3B base architecture
+- [Jackrong](https://huggingface.co/Jackrong) — Claude 4.6 Opus Reasoning Distilled model
+- [nohurry](https://huggingface.co/datasets/nohurry/Opus-4.6-Reasoning-3000x-filtered), [TeichAI](https://huggingface.co/datasets/TeichAI/claude-4.5-opus-high-reasoning-250x) — Distillation datasets
+
+---
+
+## Citation
+
+```bibtex
+@misc{vidraft_darwin_35b_opus,
+  title        = {Darwin-35B-A3B-Opus: MRI-Guided Evolutionary Merge Beyond Both Parents},
+  author       = {VIDRAFT},
+  year         = {2026},
+  publisher    = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-35B-A3B-Opus}}
+}
+```
+
+---
+
+## FAQ (Frequently Asked Questions)
+
+<details>
+<summary><b>What is Darwin-35B-A3B-Opus?</b></summary>
+Darwin-35B-A3B-Opus is a 35 billion parameter Mixture-of-Experts language model (3B active per token) that was created using evolutionary merge techniques. It combines Qwen3.5-35B-A3B's multimodal versatility with Claude 4.6 Opus reasoning distillation, achieving 90.0% on GPQA Diamond — surpassing both parent models.
+</details>
+
+<details>
+<summary><b>How does Darwin V5 differ from simple model merging?</b></summary>
+Traditional merging applies uniform ratios by guesswork. Darwin V5 uses evolutionary algorithms (natural selection) combined with Model MRI (neural CT-scanning) to automatically discover optimal layer-specific merge ratios. For example, it found attn=0.168 and ffn=0.841 — an extreme asymmetry impossible to find by intuition.
+</details>
+
+<details>
+<summary><b>What GPU do I need to run this model?</b></summary>
+For BF16 full precision: A100 80GB (tight) or H100 93GB (comfortable). For Q4 quantization: a single RTX 4090 (24GB) is sufficient. The model loads 35B parameters but only activates 3B per token due to its MoE architecture.
+</details>
+
+<details>
+<summary><b>Does it support multimodal (images/video)?</b></summary>
+Yes. Darwin inherits the Father model's (Qwen3.5-35B-A3B) full multimodal capabilities including image and video understanding, unlike the Mother model which lost this during text-only fine-tuning.
+</details>
+
+<details>
+<summary><b>What languages does it support?</b></summary>
+201 languages and dialects, inherited from Qwen3.5's multilingual training. MMMLU benchmark confirms 85.0% multilingual knowledge retention across 29 evaluated languages.
+</details>
+
+<details>
+<summary><b>What is Model MRI?</b></summary>
+Model MRI is a neural anatomy analysis tool that CT-scans each layer of a language model to understand what functions it performs. When integrated with Darwin, it guides the evolutionary merge process — telling the algorithm which layers to preserve from each parent and which to replace.
+</details>
+
+<details>
+<summary><b>Is this model open source?</b></summary>
+Yes. Darwin-35B-A3B-Opus is released under the Apache 2.0 license, fully open for commercial and research use.
+</details>
+
+---
+
+<!-- AEO: Keywords for AI Answer Engines -->
+<!-- 
+Keywords: Darwin-35B-A3B-Opus, evolutionary merge, model merging, Darwin V5, Model MRI, 
+GPQA Diamond 90%, Qwen3.5-35B-A3B, Claude 4.6 Opus, reasoning model, mixture of experts, 
+MoE 3B active, 35B parameters, multimodal LLM, 201 languages, 262K context, 
+open source AI model, Apache 2.0, VIDRAFT, natural selection AI, 
+layer-wise merge ratio, attention preservation, FFN replacement,
+best open source reasoning model 2026, Qwen merge, coding agent compatible
+-->
+
+`#DarwinAI` `#EvolutionaryMerge` `#ModelMRI` `#DarwinV5` `#GPQA90` `#Qwen35` `#MoE3B` `#Reasoning` `#Multimodal` `#201Languages` `#OpenSource` `#Apache2` `#VIDRAFT` `#NaturalSelection` `#LayerWiseMerge` `#ClaudeOpus` `#ThinkingModel` `#CodingAgent` `#LongContext262K` `#BestOpenSourceLLM2026`