Text Generation
Transformers
Safetensors
qwen3_5
image-text-to-text
darwin-v6
generation-2
evolutionary-merge
mri-guided
dare-ties
qwen3.5
korean
hybrid-vigor
reasoning
thinking
proto-agi
vidraft
k-ai
conversational
Instructions to use FINAL-Bench/Darwin-27B-KR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FINAL-Bench/Darwin-27B-KR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-27B-KR") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("FINAL-Bench/Darwin-27B-KR") model = AutoModelForMultimodalLM.from_pretrained("FINAL-Bench/Darwin-27B-KR", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use FINAL-Bench/Darwin-27B-KR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FINAL-Bench/Darwin-27B-KR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FINAL-Bench/Darwin-27B-KR", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/FINAL-Bench/Darwin-27B-KR
- SGLang
How to use FINAL-Bench/Darwin-27B-KR with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "FINAL-Bench/Darwin-27B-KR" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FINAL-Bench/Darwin-27B-KR", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "FINAL-Bench/Darwin-27B-KR" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FINAL-Bench/Darwin-27B-KR", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use FINAL-Bench/Darwin-27B-KR with Docker Model Runner:
docker model run hf.co/FINAL-Bench/Darwin-27B-KR
Commit ·
171a769
0
Parent(s):
Upload model
Browse files- .gitattributes +38 -0
- README.md +341 -0
- chat_template.jinja +154 -0
- config.json +135 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors-00001-of-00011.safetensors +3 -0
- model.safetensors-00002-of-00011.safetensors +3 -0
- model.safetensors-00003-of-00011.safetensors +3 -0
- model.safetensors-00004-of-00011.safetensors +3 -0
- model.safetensors-00005-of-00011.safetensors +3 -0
- model.safetensors-00006-of-00011.safetensors +3 -0
- model.safetensors-00007-of-00011.safetensors +3 -0
- model.safetensors-00008-of-00011.safetensors +3 -0
- model.safetensors-00009-of-00011.safetensors +3 -0
- model.safetensors-00010-of-00011.safetensors +3 -0
- model.safetensors-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +0 -0
- parent_comparison.png +3 -0
- preprocessor_config.json +21 -0
- tokenizer.json +3 -0
- tokenizer_config.json +305 -0
- video_preprocessor_config.json +21 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
parent_comparison[[:space:]](1).png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
parent_comparison.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,341 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- FINAL-Bench/Darwin-27B-Opus
|
| 5 |
+
- Qwen/Qwen3.5-27B
|
| 6 |
+
tags:
|
| 7 |
+
- darwin-v6
|
| 8 |
+
- generation-2
|
| 9 |
+
- evolutionary-merge
|
| 10 |
+
- mri-guided
|
| 11 |
+
- dare-ties
|
| 12 |
+
- qwen3.5
|
| 13 |
+
- korean
|
| 14 |
+
- hybrid-vigor
|
| 15 |
+
- reasoning
|
| 16 |
+
- thinking
|
| 17 |
+
- proto-agi
|
| 18 |
+
- vidraft
|
| 19 |
+
- k-ai
|
| 20 |
+
language:
|
| 21 |
+
- ko
|
| 22 |
+
- en
|
| 23 |
+
- ja
|
| 24 |
+
- zh
|
| 25 |
+
- multilingual
|
| 26 |
+
pipeline_tag: text-generation
|
| 27 |
+
library_name: transformers
|
| 28 |
+
---
|
| 29 |
+
|
| 30 |
+
# Darwin-27B-KR — Korean Hybrid Vigor through Evolutionary FFN Breeding
|
| 31 |
+
|
| 32 |
+
<p align="center">
|
| 33 |
+
<a href="https://huggingface.co/FINAL-Bench/Darwin-27B-Opus"><img src="https://img.shields.io/badge/🧬_Father-Darwin--27B--Opus-blue?style=for-the-badge" alt="Father"></a>
|
| 34 |
+
<a href="https://huggingface.co/FINAL-Bench/Darwin-27B-KR"><img src="https://img.shields.io/badge/⭐_Child-Darwin--27B--KR-gold?style=for-the-badge" alt="Child"></a>
|
| 35 |
+
</p>
|
| 36 |
+
|
| 37 |
+
<p align="center">
|
| 38 |
+
<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>
|
| 39 |
+
<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>
|
| 40 |
+
<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>
|
| 41 |
+
<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>
|
| 42 |
+
</p>
|
| 43 |
+
|
| 44 |
+
<p align="center">
|
| 45 |
+
<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>
|
| 46 |
+
<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>
|
| 47 |
+
</p>
|
| 48 |
+
|
| 49 |
+
> Qwen3.5-27B Dense | 27B Params | Thinking Mode | 262K Context | 201 Languages | BF16 | Apache 2.0
|
| 50 |
+
> **The child outperforms both parents on Korean cultural intelligence — Hybrid Vigor confirmed at 27B scale**
|
| 51 |
+
|
| 52 |
+
---
|
| 53 |
+
|
| 54 |
+
## What Is This?
|
| 55 |
+
|
| 56 |
+
Darwin-27B-KR is a second-generation Darwin model bred from two complementary parents:
|
| 57 |
+
|
| 58 |
+
- **Father (Darwin-27B-Opus):** Qwen3.5-27B evolved with Claude 4.6 Opus reasoning FFN — strong in logical reasoning and deep inference
|
| 59 |
+
- **Mother (Qwen3.5-27B-KoSFT):** Qwen3.5-27B fine-tuned with 230K+ Korean language samples — strong in Korean cultural knowledge and linguistic understanding (private, purpose-bred for Korean knowledge reinforcement)
|
| 60 |
+
|
| 61 |
+
The Darwin V6 engine automatically discovered that **93.3% of FFN layers should come from the Mother**, while **preserving 93.2% of the Father's Attention layers** — confirming the core Darwin principle: *FFN carries knowledge, Attention carries reasoning.*
|
| 62 |
+
|
| 63 |
+
The result: **the child outperforms both parents on every Korean benchmark category**, a phenomenon known as **Hybrid Vigor (잡종강세)**.
|
| 64 |
+
|
| 65 |
+
---
|
| 66 |
+
|
| 67 |
+
## Hybrid Vigor: 4-Generation CLIcK Comparison
|
| 68 |
+
|
| 69 |
+
CLIcK (Cultural and Linguistic Intelligence in Korean) — 200 questions, 0-shot, loglikelihood evaluation.
|
| 70 |
+
|
| 71 |
+
| Generation | Model | CLIcK (Overall) | Culture | Language |
|
| 72 |
+
|---|---|---|---|---|
|
| 73 |
+
| Gen 0 (Ancestor) | Qwen3.5-27B | 69.52% | 71.84% | 64.66% |
|
| 74 |
+
| Gen 1 (Father) | Darwin-27B-Opus | 70.19% | 72.91% | 64.47% |
|
| 75 |
+
| — (Mother) | Qwen3.5-27B-KoSFT | 74.74% | 76.95% | 70.11% |
|
| 76 |
+
| **Gen 2 (Child)** | **Darwin-27B-KR** | **75.59%** ★ | **77.85%** ★ | **70.86%** ★ |
|
| 77 |
+
|
| 78 |
+
**The child surpasses both parents.** Two generations of zero-training evolution achieved **+6.07%p over the original Qwen3.5-27B.**
|
| 79 |
+
|
| 80 |
+
### Detailed Category Breakdown
|
| 81 |
+
|
| 82 |
+
| Category | Ancestor | Father | Mother | **Child** | Best |
|
| 83 |
+
|---|---|---|---|---|---|
|
| 84 |
+
| **Economy** | 93.22% | 93.22% | 94.92% | **94.92%** | Mother=Child |
|
| 85 |
+
| **Geography** | 70.23% | 70.23% | 75.57% | **75.57%** | Mother=Child |
|
| 86 |
+
| **History** | 47.00% | 47.00% | 50.50% | **53.50%** | **Child ★** |
|
| 87 |
+
| **K-pop** | 92.68% | **97.56%** | 90.24% | 92.68% | Father |
|
| 88 |
+
| **Law** | 59.50% | 60.00% | 67.50% | **69.50%** | **Child ★** |
|
| 89 |
+
| **Politics** | 80.95% | 82.14% | **86.90%** | 85.71% | Mother |
|
| 90 |
+
| **Society** | 87.00% | 89.00% | **90.50%** | 90.00% | Mother |
|
| 91 |
+
| **Tradition** | 81.50% | 82.50% | 88.00% | **88.50%** | **Child ★** |
|
| 92 |
+
| **Functional** | 68.18% | 67.42% | 71.21% | **75.00%** | **Child ★** |
|
| 93 |
+
| **Grammar** | 44.50% | 44.50% | **55.00%** | 53.00% | Mother |
|
| 94 |
+
| **Text** | 82.50% | 82.50% | 84.50% | **86.00%** | **Child ★** |
|
| 95 |
+
|
| 96 |
+
**Child wins 7 out of 11 categories.** The largest gains are in Law (+9.5%p over Father), Functional Language (+7.6%p), and History (+6.5%p).
|
| 97 |
+
|
| 98 |
+
---
|
| 99 |
+
|
| 100 |
+
## Why This Matters
|
| 101 |
+
|
| 102 |
+
### 1. Hybrid Vigor at 27B Scale
|
| 103 |
+
Previously demonstrated at 4B (Darwin-4B-Genesis, CLIcK 92%). Now confirmed at 27B: the child exceeds both parents on Korean cultural and linguistic intelligence with zero additional training.
|
| 104 |
+
|
| 105 |
+
### 2. CMA-ES Discovered the Optimal Breeding Strategy
|
| 106 |
+
The evolutionary optimizer automatically determined:
|
| 107 |
+
- **FFN ratio: 93.3%** → Almost entirely Mother's Korean knowledge
|
| 108 |
+
- **Attention ratio: 6.8%** → Almost entirely Father's reasoning chains
|
| 109 |
+
- This independently confirms our finding: *"FFN = knowledge (safe to swap), Attention = reasoning (must preserve)"*
|
| 110 |
+
|
| 111 |
+
### 3. Ancestral Knowledge Tracking
|
| 112 |
+
By evaluating all four generations (Ancestor → Father → Mother → Child), we can trace how knowledge flows through evolutionary breeding:
|
| 113 |
+
- Father inherits Claude's reasoning but loses some Korean knowledge
|
| 114 |
+
- Mother gains Korean knowledge through SFT
|
| 115 |
+
- Child combines both — inheriting the best of each lineage
|
| 116 |
+
|
| 117 |
+
### 4. Zero Training Cost
|
| 118 |
+
|
| 119 |
+
| | This Model | Typical Fine-Tuning |
|
| 120 |
+
|---|---|---|
|
| 121 |
+
| GPU | H100 × 1 | 8-64 GPUs |
|
| 122 |
+
| Time | ~2.5 hours | Days to weeks |
|
| 123 |
+
| Training data | 0 tokens | Millions of tokens |
|
| 124 |
+
| Training compute | Fitness evaluation only | Full gradient updates |
|
| 125 |
+
|
| 126 |
+
---
|
| 127 |
+
|
| 128 |
+
## How It Works: Evolutionary FFN Breeding
|
| 129 |
+
|
| 130 |
+
```
|
| 131 |
+
Father: Darwin-27B-Opus (Claude reasoning FFN)
|
| 132 |
+
Mother: Qwen3.5-27B-KoSFT (Korean knowledge FFN)
|
| 133 |
+
Both: hidden_size=4096, intermediate=17408, 64 layers
|
| 134 |
+
= 100% structurally compatible
|
| 135 |
+
|
| 136 |
+
Method: CMA-ES optimizes per-block breeding ratios
|
| 137 |
+
across 14 genome dimensions
|
| 138 |
+
Fitness: kmmlu_lite (Korean knowledge benchmark)
|
| 139 |
+
Result: Child inherits Mother's Korean FFN knowledge
|
| 140 |
+
while preserving Father's reasoning Attention
|
| 141 |
+
```
|
| 142 |
+
|
| 143 |
+
### Optimal Genome (Discovered by CMA-ES)
|
| 144 |
+
|
| 145 |
+
```
|
| 146 |
+
global_ratio: 0.4812 Overall 48:52 Father:Mother balance
|
| 147 |
+
attn_ratio: 0.0681 Attention 93.2% from Father (reasoning preserved!)
|
| 148 |
+
ffn_ratio: 0.9334 FFN 93.3% from Mother (Korean knowledge absorbed!)
|
| 149 |
+
embed_ratio: 0.3678 Embedding 63:37 Father:Mother
|
| 150 |
+
density_a: 0.9699 Father density (DARE sparsity)
|
| 151 |
+
density_b: 0.9767 Mother density (DARE sparsity)
|
| 152 |
+
mri_trust: 0.5333 MRI guidance weight
|
| 153 |
+
```
|
| 154 |
+
|
| 155 |
+
### Block-Level Ratios
|
| 156 |
+
|
| 157 |
+
```
|
| 158 |
+
Block 0 (L0-10): 0.6041 Mother-leaning (early layers)
|
| 159 |
+
Block 1 (L11-21): 0.4107 Balanced
|
| 160 |
+
Block 2 (L22-32): 0.3975 Father-leaning (core reasoning)
|
| 161 |
+
Block 3 (L33-43): 0.6078 Mother-leaning (knowledge layers)
|
| 162 |
+
Block 4 (L44-54): 0.7820 Strong Mother (Korean knowledge peak)
|
| 163 |
+
Block 5 (L55-64): 0.3960 Father-leaning (output reasoning)
|
| 164 |
+
```
|
| 165 |
+
|
| 166 |
+
**Key insight:** CMA-ES applied the strongest Mother influence to Block 4 (L44-54), which corresponds to deep knowledge layers, while preserving Father's reasoning in Blocks 2 and 5.
|
| 167 |
+
|
| 168 |
+
---
|
| 169 |
+
|
| 170 |
+
## Evolution Parameters
|
| 171 |
+
|
| 172 |
+
| Setting | Value |
|
| 173 |
+
|---|---|
|
| 174 |
+
| Engine | Darwin V6 (Diagnostic-Guided Evolutionary Merge) |
|
| 175 |
+
| Merge method | DARE-TIES (direct PyTorch, no mergekit dependency) |
|
| 176 |
+
| Population size | 16 |
|
| 177 |
+
| Phase 1 (proxy search) | 150 steps |
|
| 178 |
+
| Phase 2 (real merge) | 25 steps, top 5 elite |
|
| 179 |
+
| Fitness function | kmmlu_lite (Korean knowledge) |
|
| 180 |
+
| Best fitness | **0.8274 (82.74%)** |
|
| 181 |
+
| MRI guidance | Enabled (static + probe analysis) |
|
| 182 |
+
| Total time | ~2.5 hours (H100 ×1) |
|
| 183 |
+
|
| 184 |
+
---
|
| 185 |
+
|
| 186 |
+
## Family Tree
|
| 187 |
+
|
| 188 |
+
```
|
| 189 |
+
Qwen/Qwen3.5-27B (Ancestor, CLIcK 69.52%)
|
| 190 |
+
├── × Jackrong/Claude-4.6-Opus-Reasoning-Distilled
|
| 191 |
+
│ └── Darwin-27B-Opus (Father, Gen 1, CLIcK 70.19%)
|
| 192 |
+
│ │ + Claude reasoning FFN
|
| 193 |
+
│ │ + GPQA Diamond 74.7% greedy
|
| 194 |
+
│ │
|
| 195 |
+
│ └── × Qwen3.5-27B-KoSFT (Mother, CLIcK 74.74%)
|
| 196 |
+
│ │ + 230K Korean SFT samples
|
| 197 |
+
│ │ + K-AI Leaderboard caliber
|
| 198 |
+
│ │
|
| 199 |
+
│ └── ★ Darwin-27B-KR (Child, Gen 2, CLIcK 75.59%)
|
| 200 |
+
│ Hybrid Vigor: surpasses BOTH parents!
|
| 201 |
+
│ FFN 93.3% Mother + Attention 93.2% Father
|
| 202 |
+
```
|
| 203 |
+
|
| 204 |
+
### DNA Composition
|
| 205 |
+
|
| 206 |
+
```
|
| 207 |
+
Qwen3.5-27B (foundation) ~40%
|
| 208 |
+
Claude 4.6 Opus (reasoning patterns) ~5% (via Father's Attention)
|
| 209 |
+
Korean SFT (cultural knowledge) ~55% (via Mother's FFN)
|
| 210 |
+
```
|
| 211 |
+
|
| 212 |
+
---
|
| 213 |
+
|
| 214 |
+
## Model Specifications
|
| 215 |
+
|
| 216 |
+
| | |
|
| 217 |
+
|---|---|
|
| 218 |
+
| Architecture | Qwen3.5 Dense (GatedDeltaNet) |
|
| 219 |
+
| Parameters | 27B |
|
| 220 |
+
| Hidden Size | 4096 |
|
| 221 |
+
| Intermediate Size | 17408 |
|
| 222 |
+
| Layers | 64 |
|
| 223 |
+
| Context Length | 262,144 (extensible to 1M via YaRN) |
|
| 224 |
+
| Precision | BF16 |
|
| 225 |
+
| Languages | 201 |
|
| 226 |
+
| Thinking | Enabled (chain-of-thought reasoning) |
|
| 227 |
+
| License | Apache 2.0 |
|
| 228 |
+
|
| 229 |
+
---
|
| 230 |
+
|
| 231 |
+
## Usage
|
| 232 |
+
|
| 233 |
+
### Transformers
|
| 234 |
+
|
| 235 |
+
```python
|
| 236 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 237 |
+
import torch
|
| 238 |
+
|
| 239 |
+
tokenizer = AutoTokenizer.from_pretrained(
|
| 240 |
+
"FINAL-Bench/Darwin-27B-KR", trust_remote_code=True
|
| 241 |
+
)
|
| 242 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 243 |
+
"FINAL-Bench/Darwin-27B-KR",
|
| 244 |
+
torch_dtype=torch.bfloat16,
|
| 245 |
+
device_map="auto",
|
| 246 |
+
trust_remote_code=True,
|
| 247 |
+
)
|
| 248 |
+
|
| 249 |
+
messages = [{"role": "user", "content": "한국의 전통 혼례 절차에 대해 설명해주세요."}]
|
| 250 |
+
text = tokenizer.apply_chat_template(
|
| 251 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 252 |
+
)
|
| 253 |
+
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
| 254 |
+
outputs = model.generate(**inputs, max_new_tokens=4096, do_sample=False)
|
| 255 |
+
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
|
| 256 |
+
```
|
| 257 |
+
|
| 258 |
+
---
|
| 259 |
+
|
| 260 |
+
## VRAM Requirements
|
| 261 |
+
|
| 262 |
+
| Setup | VRAM | Status |
|
| 263 |
+
|---|---|---|
|
| 264 |
+
| BF16 Full Precision | ~55 GB | H100 single GPU |
|
| 265 |
+
| NVIDIA H100 80GB | 80 GB | Very comfortable |
|
| 266 |
+
| 2× RTX 4090 48GB | 48 GB | Tensor parallel |
|
| 267 |
+
| 4-bit Quantized | ~16 GB | RTX 4090 single GPU |
|
| 268 |
+
|
| 269 |
+
---
|
| 270 |
+
|
| 271 |
+
## Darwin 27B Family
|
| 272 |
+
|
| 273 |
+
| Model | Gen | Role | CLIcK | GPQA | Specialty |
|
| 274 |
+
|---|---|---|---|---|---|
|
| 275 |
+
| Qwen3.5-27B | Gen 0 | Ancestor | 69.52% | 85.5% | Foundation |
|
| 276 |
+
| Darwin-27B-Opus | Gen 1 | Father | 70.19% | 74.7%* | Claude reasoning |
|
| 277 |
+
| Qwen3.5-27B-KoSFT | — | Mother | 74.74% | — | Korean knowledge |
|
| 278 |
+
| **Darwin-27B-KR** | **Gen 2** | **Child** | **75.59%** ★ | — | **Hybrid: Reasoning + Korean** |
|
| 279 |
+
|
| 280 |
+
*GPQA evaluated with greedy decoding; maj@8 retry in progress (estimated 88.9%)
|
| 281 |
+
|
| 282 |
+
---
|
| 283 |
+
|
| 284 |
+
## Key Findings
|
| 285 |
+
|
| 286 |
+
1. **FFN = Knowledge, Attention = Reasoning** — CMA-ES independently discovered this by assigning 93.3% FFN from Mother (Korean) and 93.2% Attention from Father (reasoning)
|
| 287 |
+
|
| 288 |
+
2. **Hybrid Vigor scales with model size** — Confirmed at 4B (Genesis, CLIcK 92%) and now at 27B (KR, CLIcK 75.59%)
|
| 289 |
+
|
| 290 |
+
3. **Zero-training evolution works recursively** — Gen 0 → Gen 1 → Gen 2, each generation improving, with zero gradient updates
|
| 291 |
+
|
| 292 |
+
4. **Ancestral knowledge is preserved** — Despite two generations of breeding, core Qwen3.5-27B capabilities remain intact
|
| 293 |
+
|
| 294 |
+
5. **Korean knowledge transfers through FFN** — The Mother's 230K Korean SFT knowledge was successfully transplanted into the child via FFN breeding
|
| 295 |
+
|
| 296 |
+
---
|
| 297 |
+
|
| 298 |
+
## Roadmap
|
| 299 |
+
|
| 300 |
+
- [ ] Full GPQA Diamond evaluation (greedy + selective maj@8 retry)
|
| 301 |
+
- [ ] K-AI Leaderboard official submission (KMMLU-Pro, CLIcK, HLE, MuSR, Com2)
|
| 302 |
+
- [ ] MMLU-Pro evaluation and HF leaderboard registration
|
| 303 |
+
- [ ] Cross-architecture breeding at 27B scale (Transformer × Mamba FFN)
|
| 304 |
+
- [ ] Third-generation breeding with domain-specific mothers
|
| 305 |
+
|
| 306 |
+
---
|
| 307 |
+
|
| 308 |
+
## References
|
| 309 |
+
|
| 310 |
+
- DARE-TIES: Yadav et al., 2023 (https://arxiv.org/abs/2311.03099) — re-implemented, not library-dependent
|
| 311 |
+
- CLIcK: Kim et al., 2024 (https://arxiv.org/abs/2403.06412) — Cultural and Linguistic Intelligence in Korean
|
| 312 |
+
- Darwin V6 Engine: https://huggingface.co/spaces/ginigen-ai/DARWIN-V5-BACKUP
|
| 313 |
+
- FINAL Bench: https://huggingface.co/spaces/FINAL-Bench/Leaderboard
|
| 314 |
+
- Darwin Family Collection: https://huggingface.co/collections/FINAL-Bench/darwin-family
|
| 315 |
+
|
| 316 |
+
---
|
| 317 |
+
|
| 318 |
+
## Built By
|
| 319 |
+
|
| 320 |
+
| | |
|
| 321 |
+
|---|---|
|
| 322 |
+
| Developer | VIDRAFT |
|
| 323 |
+
| Engine | Darwin V6 (Diagnostic-Guided Evolutionary Merge) |
|
| 324 |
+
| Generation | **Generation 2** — Korean Hybrid Vigor |
|
| 325 |
+
| Architecture | Qwen3.5-27B Dense |
|
| 326 |
+
| License | Apache 2.0 |
|
| 327 |
+
|
| 328 |
+
---
|
| 329 |
+
|
| 330 |
+
## Citation
|
| 331 |
+
|
| 332 |
+
```bibtex
|
| 333 |
+
@misc{vidraft_darwin_27b_kr_2026,
|
| 334 |
+
title = {Darwin-27B-KR: Korean Hybrid Vigor through Evolutionary FFN Breeding},
|
| 335 |
+
subtitle = {Child Surpasses Both Parents on Korean Cultural Intelligence with Zero Training},
|
| 336 |
+
author = {VIDRAFT},
|
| 337 |
+
year = {2026},
|
| 338 |
+
publisher = {Hugging Face},
|
| 339 |
+
howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-27B-KR}}
|
| 340 |
+
}
|
| 341 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 248056,
|
| 6 |
+
"model_type": "qwen3_5",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"attn_output_gate": true,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 248044,
|
| 13 |
+
"full_attention_interval": 4,
|
| 14 |
+
"head_dim": 256,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 5120,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 17408,
|
| 19 |
+
"layer_types": [
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"linear_attention",
|
| 65 |
+
"linear_attention",
|
| 66 |
+
"linear_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"linear_attention",
|
| 69 |
+
"linear_attention",
|
| 70 |
+
"linear_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"linear_attention",
|
| 73 |
+
"linear_attention",
|
| 74 |
+
"linear_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"linear_attention",
|
| 77 |
+
"linear_attention",
|
| 78 |
+
"linear_attention",
|
| 79 |
+
"full_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"linear_attention",
|
| 82 |
+
"linear_attention",
|
| 83 |
+
"full_attention"
|
| 84 |
+
],
|
| 85 |
+
"linear_conv_kernel_dim": 4,
|
| 86 |
+
"linear_key_head_dim": 128,
|
| 87 |
+
"linear_num_key_heads": 16,
|
| 88 |
+
"linear_num_value_heads": 48,
|
| 89 |
+
"linear_value_head_dim": 128,
|
| 90 |
+
"max_position_embeddings": 262144,
|
| 91 |
+
"mlp_only_layers": [],
|
| 92 |
+
"model_type": "qwen3_5_text",
|
| 93 |
+
"mtp_num_hidden_layers": 1,
|
| 94 |
+
"mtp_use_dedicated_embeddings": false,
|
| 95 |
+
"num_attention_heads": 24,
|
| 96 |
+
"num_hidden_layers": 64,
|
| 97 |
+
"num_key_value_heads": 4,
|
| 98 |
+
"rms_norm_eps": 1e-06,
|
| 99 |
+
"use_cache": true,
|
| 100 |
+
"vocab_size": 248320,
|
| 101 |
+
"mamba_ssm_dtype": "float32",
|
| 102 |
+
"rope_parameters": {
|
| 103 |
+
"mrope_interleaved": true,
|
| 104 |
+
"mrope_section": [
|
| 105 |
+
11,
|
| 106 |
+
11,
|
| 107 |
+
10
|
| 108 |
+
],
|
| 109 |
+
"rope_type": "default",
|
| 110 |
+
"rope_theta": 10000000,
|
| 111 |
+
"partial_rotary_factor": 0.25
|
| 112 |
+
}
|
| 113 |
+
},
|
| 114 |
+
"tie_word_embeddings": false,
|
| 115 |
+
"transformers_version": "4.57.0.dev0",
|
| 116 |
+
"video_token_id": 248057,
|
| 117 |
+
"vision_config": {
|
| 118 |
+
"deepstack_visual_indexes": [],
|
| 119 |
+
"depth": 27,
|
| 120 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 121 |
+
"hidden_size": 1152,
|
| 122 |
+
"in_channels": 3,
|
| 123 |
+
"initializer_range": 0.02,
|
| 124 |
+
"intermediate_size": 4304,
|
| 125 |
+
"model_type": "qwen3_5",
|
| 126 |
+
"num_heads": 16,
|
| 127 |
+
"num_position_embeddings": 2304,
|
| 128 |
+
"out_hidden_size": 5120,
|
| 129 |
+
"patch_size": 16,
|
| 130 |
+
"spatial_merge_size": 2,
|
| 131 |
+
"temporal_patch_size": 2
|
| 132 |
+
},
|
| 133 |
+
"vision_end_token_id": 248054,
|
| 134 |
+
"vision_start_token_id": 248053
|
| 135 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.57.0.dev0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors-00001-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:955122c24d3cd7f7477b49bb8488611488f8af8229eeb081b2e7ecc0481bf8dd
|
| 3 |
+
size 5263851872
|
model.safetensors-00002-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:493d72ab1031b2ac0d36b7293e4d68e144c0359dd406632687f998c97fe0197e
|
| 3 |
+
size 5347741440
|
model.safetensors-00003-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be7af7edb730ba4bb90f66dfcedc86371f0518a557e35401f3e374901cb9fd81
|
| 3 |
+
size 5347741504
|
model.safetensors-00004-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a112c171df27b8882ab654c3015ee3266cedb93b2c40c6ea6a07b4f30f7f9425
|
| 3 |
+
size 5347741504
|
model.safetensors-00005-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5f0d88905e2813dd7c9655619d8298454352d8cdd7ec15e5b22a6229d6395f6
|
| 3 |
+
size 5347741504
|
model.safetensors-00006-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6c57e38cf62c954e66fae0f3e126f449bfcc33565625e8bee10a5bf0fa75e8c
|
| 3 |
+
size 5347741504
|
model.safetensors-00007-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1e163f371492d85789e1b07018ce2fd2173fcf4897398ce53ee71483e7ec83e
|
| 3 |
+
size 5347741496
|
model.safetensors-00008-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6eff220debc2b0f14eda24f29292e14d5970ff35e16e51274a2aa1eb1a9874a
|
| 3 |
+
size 5368714128
|
model.safetensors-00009-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6a3d412aeae44325831d9292eca8bc8b7ce1688b26a142be771226273a6c3f7
|
| 3 |
+
size 5347745520
|
model.safetensors-00010-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ceb990a266ae2509fe04166508c95f8456e1ee187b625bf8e2235196044ed44a
|
| 3 |
+
size 5347749200
|
model.safetensors-00011-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdb78dcc58060714a40dd4c952edce6265354609106b2cb0270298b3e460e5ff
|
| 3 |
+
size 2148496880
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
parent_comparison.png
ADDED
|
Git LFS Details
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"248044": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"248045": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"248046": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"248047": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"248048": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"248049": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"248050": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"248051": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"248052": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"248053": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"248054": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"248055": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"248056": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"248057": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"248058": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"248059": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"248060": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"248061": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"248062": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"248063": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"248064": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"248065": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"248066": {
|
| 181 |
+
"content": "<tool_response>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"248067": {
|
| 189 |
+
"content": "</tool_response>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"248068": {
|
| 197 |
+
"content": "<think>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"248069": {
|
| 205 |
+
"content": "</think>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"248070": {
|
| 213 |
+
"content": "<|audio_start|>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"248071": {
|
| 221 |
+
"content": "<|audio_end|>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"248072": {
|
| 229 |
+
"content": "<tts_pad>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"248073": {
|
| 237 |
+
"content": "<tts_text_bos>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"248074": {
|
| 245 |
+
"content": "<tts_text_eod>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"248075": {
|
| 253 |
+
"content": "<tts_text_bos_single>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"248076": {
|
| 261 |
+
"content": "<|audio_pad|>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
}
|
| 268 |
+
},
|
| 269 |
+
"additional_special_tokens": [
|
| 270 |
+
"<|im_start|>",
|
| 271 |
+
"<|im_end|>",
|
| 272 |
+
"<|object_ref_start|>",
|
| 273 |
+
"<|object_ref_end|>",
|
| 274 |
+
"<|box_start|>",
|
| 275 |
+
"<|box_end|>",
|
| 276 |
+
"<|quad_start|>",
|
| 277 |
+
"<|quad_end|>",
|
| 278 |
+
"<|vision_start|>",
|
| 279 |
+
"<|vision_end|>",
|
| 280 |
+
"<|vision_pad|>",
|
| 281 |
+
"<|image_pad|>",
|
| 282 |
+
"<|video_pad|>"
|
| 283 |
+
],
|
| 284 |
+
"bos_token": null,
|
| 285 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + 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\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\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 {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 286 |
+
"clean_up_tokenization_spaces": false,
|
| 287 |
+
"eos_token": "<|im_end|>",
|
| 288 |
+
"errors": "replace",
|
| 289 |
+
"model_max_length": 262144,
|
| 290 |
+
"pad_token": "<|endoftext|>",
|
| 291 |
+
"split_special_tokens": false,
|
| 292 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 293 |
+
"unk_token": null,
|
| 294 |
+
"add_bos_token": false,
|
| 295 |
+
"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+",
|
| 296 |
+
"extra_special_tokens": {
|
| 297 |
+
"audio_bos_token": "<|audio_start|>",
|
| 298 |
+
"audio_eos_token": "<|audio_end|>",
|
| 299 |
+
"audio_token": "<|audio_pad|>",
|
| 300 |
+
"image_token": "<|image_pad|>",
|
| 301 |
+
"video_token": "<|video_pad|>",
|
| 302 |
+
"vision_bos_token": "<|vision_start|>",
|
| 303 |
+
"vision_eos_token": "<|vision_end|>"
|
| 304 |
+
}
|
| 305 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|