Upload model

.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
+parent_comparison.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+info[[:space:]](2).png filter=lfs diff=lfs merge=lfs -text
+s1.png filter=lfs diff=lfs merge=lfs -text
+s2.png filter=lfs diff=lfs merge=lfs -text
+info.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,264 @@
+---
+license: apache-2.0
+base_model:
+  - google/gemma-4-E4B-it
+  - arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled
+tags:
+  - darwin-v6
+  - evolutionary-merge
+  - mri-guided
+  - dare-ties
+  - gemma4
+  - reasoning
+  - thinking
+  - proto-agi
+  - vidraft
+language:
+  - en
+  - ko
+  - ja
+  - zh
+  - multilingual
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Darwin-4B-Opus
+
+<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>
+
+<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>
+
+> Gemma 4 Expert 4B (MoE) | Thinking Mode | 128K Context | 140+ Languages | BF16 | Apache 2.0
+
+---
+
+## Overview
+
+Darwin-4B-Opus is a reasoning-enhanced model created by merging google/gemma-4-E4B-it (Father) and arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled (Mother) using the Darwin V6 engine.
+
+Darwin V6 diagnoses both parent models at the tensor level before merging, assigning an independent optimal ratio to each tensor. This is fundamentally different from conventional merging tools that apply a single uniform ratio across all tensors.
+
+As the smallest member of the Darwin Opus family, Darwin-4B-Opus delivers Claude Opus-level reasoning distillation in a highly efficient 4B parameter MoE architecture, making it ideal for edge deployment, rapid prototyping, and resource-constrained environments while maintaining strong benchmark performance (0.8292 ARC-Challenge).
+
+---
+
+## Parent Models
+
+| Role | Model | Characteristics |
+|---|---|---|
+| Father | google/gemma-4-E4B-it | Gemma 4 Expert 4B (MoE), multimodal, 128K context, efficient inference |
+| Mother | arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled | Claude 4.6 Opus high-effort reasoning distillation, enhanced code/science/analysis |
+
+### Model Diagnostic Scan (MDS)
+
+<p align="center">
+  <img src="s1.png" alt="Father (gemma-4-E4B-it) MDS Scan" width="48%">
+  <img src="s2.png" alt="Mother (Claude-Opus-Distill) MDS Scan" width="48%">
+</p>
+
+Left: Father (gemma-4-E4B-it) — balanced generalist with low activation across most probes. Right: Mother (Claude-Opus-Distill) — strong REASONING concentration in later layers, CODE activation in late layers. The Mother shows significantly more specialized layer patterns from Claude Opus distillation.
+
+---
+
+## Benchmarks
+
+| Benchmark | Darwin-4B-Opus | Condition |
+|---|---|---|
+| ARC-Challenge | 82.92% | loglikelihood, zero-shot |
+
+Note: Gemma 4 architecture (Gemma4ForConditionalGeneration) has limited compatibility with lm-eval's loglikelihood method due to its multimodal wrapper structure. Only generative evaluation produces valid results for Gemma 4 based models. Full extended evaluation with Majority Voting is planned.
+
+---
+
+## Darwin V6 vs Conventional Merging
+
+| Capability | mergekit (DARE-TIES) | Darwin V6 |
+|---|---|---|
+| Implementation | Library call (mergekit CLI) | Direct PyTorch tensor operations, no external dependency |
+| Ratio selection | Uniform ratio across all tensors | Per-tensor ratio from MDS diagnostic (independent ratios per tensor) |
+| Pre-merge analysis | None | Static tensor profiling (entropy, std, norm) + probe-based functional importance (5 probes) |
+| Ratio formula | Human-set or grid search | combined = static × 0.4 + probe × 0.6, then evolutionary optimization |
+| Transplant | Not supported | ratio < 0.15 → Father 100%, ratio > 0.85 → Mother 100% (zero interpolation noise) |
+| Post-merge validation | Benchmark score only | Layer-by-layer Health Check: child vs both parents, interference and function loss detection |
+| Search method | Manual tuning | CMA-ES evolution with adaptive 14-dimensional genome |
+| Reproducibility | Config file | genome_hash seed guarantees identical output for identical genome |
+| GPU efficiency | Single merge per run | Phase 1 proxy (200 steps, seconds) → Phase 2 real merge (top-k only evaluated) |
+
+---
+
+## How Darwin V6 Works
+
+Darwin V6 does not use mergekit or any external merge library. It re-implements DARE-TIES (Yadav et al., 2023) directly via PyTorch tensor operations with per-tensor diagnostic ratios.
+
+Before merging, Darwin performs a Model Diagnostic Scan (MDS) on both parents. For every tensor, it measures Shannon entropy (information density), standard deviation (activation spread), and L2 norm (energy). Additionally, 5 diagnostic probes (REASONING, CODE, MATH, KNOWLEDGE, LANGUAGE) are passed through the model, measuring cosine distance when each layer is skipped to determine functional importance.
+
+The final merge ratio for each tensor:
+
+```
+static_score = entropy × 0.3 + std × 0.2 + clamp(norm, 100) × 0.002
+probe_score  = Σ(cosine_distance[probe_i] × weight_i)
+combined     = static × 0.4 + probe × 0.6
+mri_ratio    = combined_b / (combined_a + combined_b)
+final_ratio  = mri_ratio × mri_trust + genome_ratio × (1 - mri_trust)
+```
+
+The mri_trust parameter itself is optimized by the CMA-ES evolutionary algorithm, allowing the system to automatically determine the optimal balance between diagnostic prescription and evolutionary search for each model pair.
+
+### Parent Comparison (MDS Result)
+
+<p align="center">
+  <img src="parent_comparison.png" alt="Parent Comparison — Layer-wise Importance" width="100%">
+</p>
+
+---
+
+## Evolution Result
+
+| | |
+|---|---|
+| Best Score (ARC-Challenge) | 0.8292 |
+| Merge Method | DARE-TIES (direct PyTorch) |
+| Health Check | Not performed |
+
+Optimal Genome (14-dimensional adaptive):
+
+```
+global_ratio:        0.4989   (overall merge ratio — near balanced)
+attn_ratio:          0.1766   (Attention layers — Father strongly dominant)
+ffn_ratio:           0.9021   (FFN layers — Mother strongly dominant)
+embed_ratio:         0.6122   (Embedding — slight Mother bias)
+density_a:           0.9951   (Father DARE density — nearly full)
+density_b:           0.9617   (Mother DARE density — high)
+block_0_ratio:       0.5740   (early layers — slight Mother bias)
+block_1_ratio:       0.5811   (early-mid layers — slight Mother bias)
+block_2_ratio:       0.5736   (mid layers — slight Mother bias)
+block_3_ratio:       0.4697   (mid-late layers — near balanced, slight Father)
+block_4_ratio:       0.4930   (late layers — near balanced)
+block_5_ratio:       0.8418   (final layers, reasoning core — Mother dominant)
+mri_trust:           0.4907   (MDS 49% + Genome 51% — near equal trust)
+merge_method_weight: 0.3623
+```
+
+Key observations from the genome: ffn_ratio=0.90 indicates the FFN layers strongly favor the Mother (Claude Opus Distill), carrying the bulk of the reasoning enhancement. block_5 (final layers)=0.84 shows the reasoning core layers also strongly favor Mother, consistent with the pattern seen across all Darwin Opus models where Claude's reasoning capability concentrates in the final layers. Meanwhile, attn_ratio=0.18 firmly preserves Father's attention structure, maintaining the original Gemma 4 multimodal and context capabilities. Notably, mri_trust=0.49 shows the system found near-equal value in both diagnostic analysis and evolutionary search, suggesting a well-balanced optimization.
+
+---
+
+## Model Specifications
+
+| | |
+|---|---|
+| Architecture | Gemma 4 Expert 4B (Mixture of Experts) |
+| Parameters | 4B |
+| Precision | BF16 |
+| Context | 128K |
+| Languages | 140+ |
+| Thinking | enable_thinking=True chain-of-thought |
+| License | Apache 2.0 |
+
+---
+
+## Usage
+
+### Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("FINAL-Bench/Darwin-4B-Opus", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    "FINAL-Bench/Darwin-4B-Opus",
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+messages = [{"role": "user", "content": "Prove that sqrt(2) is irrational."}]
+text = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True, enable_thinking=True
+)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=4096, do_sample=False)
+print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+```
+
+---
+
+## VRAM Requirements
+
+| Setup | VRAM | Status |
+|---|---|---|
+| BF16 Full Precision | ~8 GB | |
+| NVIDIA RTX 4090 24GB | 24 GB | Single GPU, very comfortable |
+| NVIDIA RTX 3090 24GB | 24 GB | Single GPU, comfortable |
+| NVIDIA RTX 4080 16GB | 16 GB | Single GPU |
+| NVIDIA T4 16GB | 16 GB | Cloud/Colab friendly |
+
+Darwin-4B-Opus is the most accessible model in the Darwin Opus family, running comfortably on a single consumer GPU.
+
+---
+
+## Darwin Opus Family
+
+| Model | Architecture | Parameters | Context | Base |
+|---|---|---|---|---|
+| **Darwin-4B-Opus** | MoE (E4B) | 4B | 128K | gemma-4-E4B-it |
+| Darwin-9B-Opus | — | 9B | — | gemma-4-9B-it |
+| Darwin-31B-Opus | Dense | 31B | 256K | gemma-4-31B-it |
+| Darwin-35B-A3B-Opus | MoE | 35B (3B active) | 256K | gemma-4-35B-A3B-it |
+
+---
+
+## References
+
+- DARE-TIES: Yadav et al., 2023 (https://arxiv.org/abs/2311.03099) — re-implemented, not library-dependent
+- Darwin V6 Engine: https://huggingface.co/spaces/ginigen-ai/DARWIN-V5-BACKUP
+- FINAL Bench: https://huggingface.co/spaces/FINAL-Bench/Leaderboard
+
+---
+
+## Built By
+
+| | |
+|---|---|
+| Developer | VIDRAFT |
+| Engine | Darwin V6 (Diagnostic-Guided Evolutionary Merge) |
+| Architecture | Gemma-4-E4B (MoE) |
+| License | Apache 2.0 |
+
+---
+
+## Citation
+
+```bibtex
+@misc{vidraft_darwin_4b_opus,
+  title        = {Darwin-4B-Opus: Diagnostic-Guided Evolutionary Merge on Gemma 4 E4B},
+  author       = {VIDRAFT},
+  year         = {2026},
+  publisher    = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-4B-Opus}}
+}
+```
+This model is introduced in [Darwin Family](https://arxiv.org/abs/2605.14386).

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 +1,197 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "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",
+    "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": "5.5.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "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": "5.5.0.dev0",
+  "stop_strings": [
+    "<|im_end|>",
+    "<|im_start|>",
+    "<turn|>"
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e366af4cd8a1652dc25b81cd76a74af9d8660ead4bad2408a66881c9fc83adb
+size 15992595852

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

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>"
+}