Upload model

Co-authored-by: nielsr <nielsr@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,41 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+이문세[[:space:]]원곡.mp3 filter=lfs diff=lfs merge=lfs -text
+music.mp3 filter=lfs diff=lfs merge=lfs -text
+ffe25cfe-4e95-4398-bc6d-94d78c566316.webp filter=lfs diff=lfs merge=lfs -text
+tree.webp filter=lfs diff=lfs merge=lfs -text
+tree.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,235 @@
+---
+base_model:
+- FINAL-Bench/Darwin-4B-David
+- Qwen/Qwen3.5-4B
+language:
+- 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:
+      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
+---
+
+> ### 📱 Run it on your phone or a GPU-less PC → **POCKET**  ·  🚀 **[Try it live (CPU chat)](https://huggingface.co/spaces/FINAL-Bench/POCKET-35B-CPU)**
+> VIDRAFT's on-device family: a 35B model that runs on **iPhone** and on **CPU with no GPU** — stock `llama.cpp`, no fork.
+>
+> [![Live demo](https://img.shields.io/badge/🤗_Space-POCKET_CPU_chat-ffce3a)](https://huggingface.co/spaces/FINAL-Bench/POCKET-35B-CPU) [![Collection](https://img.shields.io/badge/📚-POCKET_collection-5dbf9a)](https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6) [![35B](https://img.shields.io/badge/POCKET--35B-GGUF-243456)](https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF) [![KR MLX](https://img.shields.io/badge/POCKET--KR-iPhone-0f6e56)](https://huggingface.co/FINAL-Bench/POCKET-KR-MLX) [![EN](https://img.shields.io/badge/POCKET--EN-GGUF-185fa5)](https://huggingface.co/FINAL-Bench/POCKET-EN-GGUF)
+
+>
+
+
+# Darwin-4B-Genesis
+
+<p align="center">
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-4B-Opus"><img src="https://img.shields.io/badge/🧬_Gen1-Darwin--4B--Opus-blue?style=for-the-badge" alt="Gen1"></a>
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-4B-David"><img src="https://img.shields.io/badge/🧬_Gen2-Darwin--4B--David-blue?style=for-the-badge" alt="Gen2"></a>
+  <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>
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-31B-Opus"><img src="https://img.shields.io/badge/🧬_Model-Darwin--31B--Opus-blue?style=for-the-badge" alt="31B"></a>
+  <a href="https://huggingface.co/spaces/FINAL-Bench/Darwin-31B-Opus"><img src="https://img.shields.io/badge/🚀_Space-31B_Demo-purple?style=for-the-badge" alt="31B Space"></a>
+</p>
+
+<p align="center">
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-35B-A3B-Opus"><img src="https://img.shields.io/badge/🧬_Model-Darwin--35B--A3B--Opus-blue?style=for-the-badge" alt="35B"></a>
+  <a href="https://huggingface.co/spaces/FINAL-Bench/Darwin-35B-A3B-Opus"><img src="https://img.shields.io/badge/🚀_Space-35B_Demo-purple?style=for-the-badge" alt="35B Space"></a>
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-35B-A3B-Opus-Q8-GGUF"><img src="https://img.shields.io/badge/📦_GGUF-Q8--Official-yellow?style=for-the-badge" alt="Q8 GGUF"></a>
+  <a href="https://huggingface.co/bartowski/FINAL-Bench_Darwin-35B-A3B-Opus-GGUF"><img src="https://img.shields.io/badge/📦_GGUF-bartowski-yellow?style=for-the-badge" alt="bartowski GGUF"></a>
+</p>
+
+<p align="center">
+  <a href="https://huggingface.co/spaces/FINAL-Bench/Leaderboard"><img src="https://img.shields.io/badge/🏆_FINAL_Bench-Leaderboard-green?style=for-the-badge" alt="FINAL Bench"></a>
+  <a href="https://huggingface.co/spaces/FINAL-Bench/all-bench-leaderboard"><img src="https://img.shields.io/badge/📊_ALL_Bench-Leaderboard-orange?style=for-the-badge" alt="ALL Bench"></a>
+</p>
+
+> **World's first Transformer × Mamba evolutionary cross-architecture FFN breeding** | CLIcK 92% | MuSR 70% | A 4B model outperforming 27B | CMA-ES 42-dimensional genome search | Hybrid Vigor demonstrated | Apache 2.0
+
+---
+
+## What Is This?
+
+Darwin-4B-Genesis is the 3rd generation Darwin model and the **world's first model to successfully crossbreed FFN layers across different architectures** — Transformer (Gemma4) and Mamba (Qwen3.5 GatedDeltaNet) — using evolutionary optimization.
+
+The father's Attention layers (Gemma4 Transformer) are preserved at 100%, while the mother's FFN knowledge (Qwen3.5 Mamba) is transplanted at layer-specific optimal ratios discovered automatically by CMA-ES across 42 dimensions.
+
+The result: the child **outperforms both parents on every benchmark** — a phenomenon known as **Hybrid Vigor**.
+
+---
+
+<p align="center">
+  <img src="tree.png" alt="Darwin-4B-Genesis" width="100%">
+</p>
+
+
+## Why This Matters
+
+### 1. World First
+
+Existing hybrid models (Jamba, Nemotron-H, Granite 4.0) are all **designed and trained from scratch**. Darwin-4B-Genesis takes **two already-trained models** from different architecture families and breeds them evolutionarily — with **zero additional training**.
+
+### 2. Hybrid Vigor Demonstrated
+
+| Benchmark | David (Father) | Qwen3.5-4B (Mother) | **Genesis (Child)** |
+|---|---|---|---|
+| CLIcK | 90% | ~50% (est.) | **92%** ✅ |
+| MuSR | 65% | ~55% (est.) | **70%** ✅ |
+
+The child surpasses **both** parents. This is the first demonstration of Hybrid Vigor in AI model breeding.
+
+---
+
+## Benchmarks
+
+| Benchmark | Genesis | David (Gen2) | K-AI #1 (27B) |
+|---|---|---|---|
+| **CLIcK** (Korean culture) | **92%** | 90% | 0.794 |
+| **MuSR** (multi-step reasoning) | **70%** | 65% | 0.604 |
+| **GPQA** (deep reasoning) | ~60% | ~60% | — |
+
+---
+
+## How It Works
+
+### Cross-Architecture FFN Breeding
+
+```
+Father: Darwin-4B-David (Gemma4 Transformer, hidden=2560, 42 layers)
+Mother: Qwen/Qwen3.5-4B (GatedDeltaNet/Mamba, hidden=2560, 32 layers)
+
+Key insight: hidden_size matches (2560) → direct FFN replacement possible
+Method: Attention 100% from Father, FFN blended at per-layer optimal ratios
+Optimizer: CMA-ES (Covariance Matrix Adaptation Evolution Strategy)
+Genome: 42 dimensions (one ratio per layer)
+Fitness: CLIcK 60% + MuSR 40% composite score
+Frozen layers: L15, L16, L22, L23, L24, L25 (Korean language preservation)
+```
+
+### Optimal Genome Discovered by CMA-ES
+
+```
+L00: 0.206  ██████████░  21% Qwen
+L07: 0.000  ░░░░░░░░░░░  Auto-protected by CMA-ES
+L15: 0.000  ░░░░░░░░░░░  Frozen (Korean)
+L22: 0.000  ░░░░░░░░░░░  Frozen (Korean)
+L29: 0.291  ██████████████░  29% Qwen (maximum)
+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.
+
+---
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained(
+    "FINAL-Bench/Darwin-4B-Genesis",
+    trust_remote_code=True,
+)
+model = AutoModelForCausalLM.from_pretrained(
+    "FINAL-Bench/Darwin-4B-Genesis",
+    dtype="bfloat16",
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+messages = [{"role": "user", "content": "Explain how hybrid vigor works in genetics."}]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=1024, do_sample=False)
+print(tokenizer.decode(outputs[0][inputs['input_ids'].shape[-1]:], skip_special_tokens=True))
+```
+
+---
+
+## 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%) ★
+```
+
+---
+
+## Citation
+
+```bibtex
+@misc{vidraft_darwin_4b_genesis,
+  title        = {Darwin-4B-Genesis: World's First Cross-Architecture FFN Breeding},
+  author       = {VIDRAFT},
+  year         = {2026},
+  publisher    = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-4B-Genesis}}
+}
+
+@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}
+}
+```

chat_template.jinja

@@ -0,0 +1,263 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(prev_message_type=None) -%}
+{%- set loop_messages = messages -%}
+{{ bos_token }}
+{#- Handle System/Tool Definitions Block -#}
+{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+    {{- '<|turn>system\n' -}}
+
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking is defined and enable_thinking -%}
+        {{- '<|think|>' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+
+    {%- if messages[0]['role'] in ['system', 'developer'] -%}
+        {{- messages[0]['content'] | trim -}}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+        {{- '<|turn>' + role + '\n' }}
+
+            {%- if message['tool_calls'] -%}
+                {%- for tool_call in message['tool_calls'] -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {{- function['arguments'] -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- if message['tool_responses'] -%}
+                {#- Tool Response handling -#}
+                {%- for tool_response in message['tool_responses'] -%}
+                    {{- '<|tool_response>' -}}
+                    {%- if tool_response['response'] is mapping -%}
+                        {{- 'response:' + tool_response['name'] | default('unknown') + '{' -}}
+                        {%- for key, value in tool_response['response'] | dictsort -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- if not loop.last %},{% endif -%}
+                        {%- endfor -%}
+                        {{- '}' -}}
+                    {%- else -%}
+                        {{- 'response:' + tool_response['name'] | default('unknown') + '{value:' + format_argument(tool_response['response'], escape_keys=False) + '}' -}}
+                    {%- endif -%}
+                    {{- '<tool_response|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_response' -%}
+            {%- endif -%}
+
+            {%- if message['content'] is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item['type'] == 'image' -%}
+                        {{- '\n\n<|image|>\n\n' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '\n\n<|video|>\n\n' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+        {%- if not (message['tool_responses'] and not message['content']) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<|turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,117 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": null,
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 18,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": null,
+  "vision_soft_tokens_per_image": 280
+}

generation_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.6.0.dev0",
+  "stop_strings": [
+    "<|im_end|>",
+    "<|im_start|>",
+    "<turn|>"
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55c85d7d21c6ec45de9cded3d8e444e1a19dbdebba36994a76e75db5a72373b
+size 15036233372

music.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b98b8056d2dac9606f5059baaaeb8c26c4ffb3fcd63e3cc6b7fa3ad8401d36
+size 3104413

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c18ffebe9ef41e463a6c99b4a23736b91ed4a2588cbfe761fef29bfd3688cf
+size 32169725

tokenizer_config.json

@@ -0,0 +1,95 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}