Duplicate from FINAL-Bench/Darwin-28B-Opus

Co-authored-by: VIDRAFT_LAB <SeaWolf-AI@users.noreply.huggingface.co>

.eval_results/gpqa_diamond.yaml

@@ -0,0 +1,9 @@
+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 88.89
+  date: '2026-04-27'
+  source:
+    url: https://huggingface.co/FINAL-Bench/Darwin-28B-Opus
+    name: Model Card
+  notes: "Standard inference, Pass@1"

.gitattributes

@@ -0,0 +1,36 @@
+*.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

README.md

@@ -0,0 +1,219 @@
+---
+license: apache-2.0
+language:
+  - en
+  - zh
+  - ko
+  - ja
+  - multilingual
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+  - darwin
+  - darwin-v7
+  - evolutionary-merge
+  - merge
+  - mergekit
+  - reasoning
+  - advanced-reasoning
+  - chain-of-thought
+  - thinking
+  - qwen3.6
+  - qwen
+  - claude-opus
+  - distillation
+  - multilingual
+  - gpqa
+  - benchmark
+  - open-source
+  - apache-2.0
+  - hybrid-vigor
+  - proto-agi
+  - vidraft
+  - eval-results
+
+base_model_relation: merge
+model-index:
+- name: Darwin-28B-Opus
+  results:
+  - task:
+      type: question-answering
+      name: Question Answering
+    dataset:
+      name: GPQA Diamond
+      type: Idavidrein/gpqa
+      config: gpqa_diamond
+    metrics:
+    - type: accuracy
+      value: 88.89
+      name: Accuracy
+---
+
+# Darwin-28B-Opus — Qwen3.6-27B × Opus-Distilled Evolutionary Merge
+
+<p align="center">
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-28B-Opus"><img src="https://img.shields.io/badge/⭐_GPQA_Diamond-88.89%25_Darwin--28B--Opus-gold?style=for-the-badge" alt="GPQA"></a>
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-36B-Opus"><img src="https://img.shields.io/badge/🧬_Sibling-Darwin--36B--Opus_(88.4%25)-blue?style=for-the-badge" alt="36B"></a>
+</p>
+
+<p align="center">
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-4B-Genesis"><img src="https://img.shields.io/badge/🧬_Model-Darwin--4B--Genesis-blue?style=for-the-badge" alt="Genesis"></a>
+  <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/FINAL-Bench/Darwin-9B-NEG"><img src="https://img.shields.io/badge/⚡_Model-Darwin--9B--NEG_(84.3%25)-purple?style=for-the-badge" alt="NEG"></a>
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-27B-Opus"><img src="https://img.shields.io/badge/🧬_Model-Darwin--27B--Opus_(86.9%25)-blue?style=for-the-badge" alt="27B"></a>
+</p>
+
+<p align="center">
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-31B-Opus"><img src="https://img.shields.io/badge/🧬_Model-Darwin--31B--Opus_(85.9%25)-blue?style=for-the-badge" alt="31B"></a>
+  <a href="https://huggingface.co/FINAL-Bench/Darwin-36B-Opus"><img src="https://img.shields.io/badge/⭐_Model-Darwin--36B--Opus_(88.4%25)-blue?style=for-the-badge" alt="36B"></a>
+</p>
+
+<p align="center">
+  <a href="https://huggingface.co/collections/FINAL-Bench/darwin-family"><img src="https://img.shields.io/badge/🏠_Darwin_Family-Collection-green?style=for-the-badge" alt="Family"></a>
+  <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>
+</p>
+
+> Qwen3.6-27B dense · 27.6B parameters · Hybrid Linear/Full Attention · BF16 · Thinking Mode · Apache 2.0
+> **Darwin V7 evolutionary merge: Father × Opus-distilled Mother → 88.89% on GPQA Diamond (3-stage adaptive evaluation)**
+
+---
+
+## Abstract
+
+**Darwin-28B-Opus** is the first reasoning model of the Darwin series built on the **Qwen3.6 generation** backbone. Produced by the Darwin V7 evolutionary breeding engine from two publicly available parents, it combines the strong bilingual reasoning of Qwen3.6-27B with Claude Opus 4-style chain-of-thought distilled behaviour.
+
+On the **GPQA Diamond** graduate-level reasoning benchmark (198 PhD-level questions), Darwin-28B-Opus scores **88.89 %** under the standard 3-stage adaptive evaluation, slightly edging out its larger MoE sibling Darwin-36B-Opus (88.4 %) and clearly surpassing its Qwen3.5-generation counterpart Darwin-27B-Opus (86.9 %).
+
+---
+
+## 🧬 Model Lineage
+
+| Role | Model | Role in the Merge |
+|:---:|:---|:---|
+| **Father (父)** | [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B) | Qwen3.6 generation dense backbone with hybrid linear/full attention. |
+| **Mother (母)** | [`rico03/Qwen3.6-27B-Claude-Opus-Reasoning-Distilled`](https://huggingface.co/rico03/Qwen3.6-27B-Claude-Opus-Reasoning-Distilled) | Claude Opus reasoning-distilled variant of the same backbone (Jackrong-style distillation, 14 k traces). |
+| **Offspring** | **`Darwin-28B-Opus`** (this model) | Darwin V7 evolutionary merge; Qwen3.6 architecture retained, Opus reasoning style inherited. |
+
+> **Why 28B?** The `28B` label denotes the Qwen3.6-generation member of the Darwin lineup (`+1` over the Qwen3.5-era `Darwin-27B-Opus`).
+> The actual parameter count is **27.6 B**, and the architecture exactly follows Qwen3.6-27B.
+
+---
+
+## ⚙️ Technical Specifications
+
+| Component | Value |
+|:---|:---|
+| Architecture | `Qwen3_5ForConditionalGeneration` (Qwen3.6 generation, hybrid linear + full attention) |
+| Parameters | **27.6 B** (BF16) |
+| Hidden size | 5 120 |
+| Intermediate size | 17 408 |
+| Head dim | 256 |
+| Layers | 64 (3 linear : 1 full attention, `full_attention_interval = 4`) |
+| Precision | bfloat16 |
+| Context length | Inherited from base (long-chain reasoning supported) |
+| License | Apache 2.0 |
+
+---
+
+## 🏆 Benchmark — GPQA Diamond (198 questions)
+
+Darwin-28B-Opus is evaluated under our standard **3-stage adaptive evaluation** protocol, identical to the protocol used across the Darwin series.
+
+| Stage | Decoding Protocol | Cost | **Accuracy** |
+|:---:|:---|:---:|:---:|
+| **Stage 1** | Single-shot greedy baseline | 1× | **74.75 %** (148 / 198) |
+| **Stage 2** | Majority vote ×8 at temperature 0.7 on Stage-1 wrongs | 8× | **83.84 %** (166 / 198) |
+| **Stage 3** | Adaptive ensemble refinement (close-tie tiebreaker + iterative MTI on residual hard questions) | ≈ 20× | **🥇 88.89 %** (176 / 198) |
+
+**Key performance indicators**:
+- Stage 1 → Stage 3: **+14.14 %p** through adaptive protocol
+- vs Darwin-27B-Opus (86.9 %): **+1.99 %p**
+- vs Darwin-36B-Opus (88.4 %): **+0.49 %p**
+- vs Darwin-31B-Opus (85.9 %): **+2.99 %p**
+
+---
+
+## 🚀 Usage
+
+### Standard inference (Stage 1 baseline)
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+tok = AutoTokenizer.from_pretrained(
+    "FINAL-Bench/Darwin-28B-Opus",
+    trust_remote_code=True,
+)
+model = AutoModelForCausalLM.from_pretrained(
+    "FINAL-Bench/Darwin-28B-Opus",
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+messages = [
+    {"role": "user",
+     "content": "Solve: If f(x) = x³ − 3x + 2, find all critical points and classify them."}
+]
+text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tok(text, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=2048, do_sample=False)
+print(tok.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
+```
+
+### Enhanced accuracy (Stage 2-3 adaptive)
+
+For leaderboard-grade accuracy, combine:
+1. Stage 1 greedy baseline,
+2. Stage 2 maj@8 temperature sampling on low-confidence answers,
+3. Stage 3 adaptive refinement on still-disputed answers.
+
+Reference implementation is provided in the Darwin-series evaluation harness.
+
+---
+
+## 🎯 Recommended Use-Cases
+
+- **Graduate-level STEM reasoning** (GPQA / science qualifying exams)
+- **Mathematical problem solving** (MATH, AIME-style problems)
+- **Code generation and debugging** (HumanEval, MBPP)
+- **Complex multi-step chain-of-thought tasks**
+- **Bilingual reasoning** (strong English + Korean; also Chinese / Japanese)
+
+## ⚠️ Limitations
+
+- At 27.6 B parameters in bfloat16, full inference requires ≈ 55 GB of VRAM (e.g., a single A100-80GB or B200).
+- Optimised for English first, with secondary support for Korean, Chinese, and Japanese.
+- Deep Opus-style reasoning traces tend to be verbose — control with `max_new_tokens` as needed.
+
+---
+
+## 📚 Citation
+
+```bibtex
+@misc{darwin28b_opus_2026,
+  title  = {Darwin-28B-Opus: Evolutionary Merging of Qwen3.6-27B with Claude-Opus-Distilled Reasoning},
+  author = {FINAL-Bench / Darwin Research Team},
+  year   = {2026},
+  howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-28B-Opus}},
+  note   = {Darwin V7 · Mother-centric Ratio Interpolation merge · 88.89 % GPQA Diamond (3-stage)}
+}
+```
+
+---
+
+## 🔗 Related Darwin Models
+
+- **Darwin-36B-Opus** — MoE 36B, Qwen3.6-35B-A3B × Opus distilled, GPQA 88.4 %
+- **Darwin-31B-Opus** — 31B dense, multilingual-strong reasoning, GPQA 85.9 %
+- **Darwin-27B-Opus** — 27B dense (Qwen3.5 generation), GPQA 86.9 %
+- **Darwin-9B-NEG** — 9B with Native Entropy Gating, GPQA 84.3 %
+- **Darwin-9B-Opus** — the Qwen3.5-9B Darwin member
+- **Darwin-4B-Genesis** — smallest Darwin member
+
+---
+
+This model is introduced in [Darwin Family](https://arxiv.org/abs/2605.14386).
+
+*Darwin V7 · Qwen3.6 generation flagship · Sealed 2026-04-25 · FINAL-Bench*

chat_template.jinja

@@ -0,0 +1,88 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant
+<think>
+' }}
+{%- endif %}

config.json

@@ -0,0 +1,147 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "bos_token_id": null,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 248046,
+    "image_token_id": 248056,
+    "language_model_only": false,
+    "model_name": "unsloth/Qwen3.6-27B",
+    "model_type": "qwen3_5",
+    "pad_token_id": 248055,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": 248044,
+        "torch_dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 5120,
+        "initializer_range": 0.02,
+        "intermediate_size": 17408,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 48,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 24,
+        "num_hidden_layers": 64,
+        "num_key_value_heads": 4,
+        "output_gate_type": "swish",
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "rope_type": "default"
+        },
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "unsloth_version": "2026.4.7",
+    "use_cache": false,
+    "video_token_id": 248057,
+    "vision_config": {
+        "deepstack_visual_indexes": [],
+        "depth": 27,
+        "torch_dtype": "bfloat16",
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4304,
+        "model_type": "qwen3_5",
+        "num_heads": 16,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 5120,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abed7b0a601b5837427b299e44faad8ad0ec64bdce16da2147736eeff4bb86a9
+size 2542796896

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfea6179fdf0e2900170a052aff9a0823132a3ff172f567195ec41418538146b
+size 4244742312

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d464035c75f903dce196564319486da0a73b778171c81c5408f19219fa25688
+size 4250052512

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d1ea501c1fe68e3303b9d4cc19cadf0bba149e04eda4f607d7d55ed3993c45
+size 4178783544

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f3e0b86667e2194cf55b38c6b1ff38f0adfb5dfbc39148df7d3163630bcfb2
+size 4167220840

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315d29b904f286da86eab61ea8f6458394545ee7a8aced6fd14e17e2b9d43531
+size 4198700520

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226ce99e4f4865f027a09061a239b8b3eed25ac3c0cfc62aebf1a3c0638078e1
+size 4187137824

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6683b2a7e78f39a29fbbb9aecb9105175b99fca323d2f442c9a7bd873bef536e
+size 4178783544

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d3b4d67d3204c3cc5ffac06faf01a5eb8ca129168e13a9d0295452f5ccb69d
+size 4167220840

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f1136b2b6cc6965d02d65e8b70f7c094e4aa6ddcb9521d4ca16d1fb629375d
+size 4220736832

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b6a57bc0d678d706ceb6d6952dab36b6064639dc33377ef770c60cd8842b30
+size 4187137824

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151a4c6b506bc73c76c33e910cee35dc3ea834e746fcc4ff9279718160c4c744
+size 4178783544

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604624a9c06bf6d91188366b4601816e97de311c9f14d4521ef8e092980712d3
+size 4145184504

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b098d824d2e1085163b455e070a1b8293955ff1829003184e6d6e30ec3a62b1
+size 2715725264

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "patch_size": 16,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Qwen3VLProcessor",
+  "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,300 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  },
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n<think>\n' }}\n{%- endif %}"
+}