Instructions to use Anserwise/AWAXIS-Think-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Anserwise/AWAXIS-Think-27b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Anserwise/AWAXIS-Think-27b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Anserwise/AWAXIS-Think-27b")
model = AutoModelForMultimodalLM.from_pretrained("Anserwise/AWAXIS-Think-27b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
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 Anserwise/AWAXIS-Think-27b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Anserwise/AWAXIS-Think-27b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Anserwise/AWAXIS-Think-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Anserwise/AWAXIS-Think-27b

SGLang

How to use Anserwise/AWAXIS-Think-27b 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 "Anserwise/AWAXIS-Think-27b" \
    --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": "Anserwise/AWAXIS-Think-27b",
		"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 "Anserwise/AWAXIS-Think-27b" \
        --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": "Anserwise/AWAXIS-Think-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Anserwise/AWAXIS-Think-27b with Docker Model Runner:
```
docker model run hf.co/Anserwise/AWAXIS-Think-27b
```

AWAXIS-Think-27b / README.md

Anserwise

Update transformers requirement to >=5.5.4 to fix qwen3_5_text loading error

dff8872 verified about 2 months ago

preview code

raw

history blame contribute delete

3.67 kB

	---
	language:
	- ko
	- en
	- ja
	- zh
	- multilingual
	license: apache-2.0
	tags:
	- qwen3.5
	- korean
	- reasoning
	- thinking
	- sft
	- k-ai
	base_model:
	- FINAL-Bench/Darwin-27B-Opus
	pipeline_tag: text-generation
	library_name: transformers
	---

	# AWAXIS-Think-27b

	[FINAL-Bench/Darwin-27B-Opus](https://huggingface.co/FINAL-Bench/Darwin-27B-Opus) 기반, 한국어 특화 고품질 SFT를 수행한 추론 모델입니다.

	> ⚠️ Requirements / Loading 주의
	> 이 모델은 `model_type: qwen3_5_text` (Qwen3.5 하이브리드 아키텍처)를 사용합니다.
	> `transformers >= 5.5.4` 이상 에서만 정상 로드됩니다.
	>
	> ```bash
	> pip install --upgrade "transformers>=5.5.4"
	> # 또는 최신 개발판
	> pip install "transformers @ git+https://github.com/huggingface/transformers.git@main"
	> ```
	>
	> 구버전 transformers에서 나타나는 `model_type 'qwen3_5_text'를 인식하지 못함` 오류는
	> 라이브러리 미업데이트로 인한 것이며, 위 명령으로 해결됩니다.

	## Method

	- Base Model: [Darwin-27B-Opus](https://huggingface.co/FINAL-Bench/Darwin-27B-Opus) (Qwen3.5-27B family)
	- Korean SFT: 한국어 문화, 역사, 법률, 경제, 사회, 지리 등 한국 특화 지식 중심의 고품질 instruction 데이터로 Supervised Fine-Tuning 수행
	- Thinking Mode: `<think>` 태그를 통한 Chain-of-Thought 단계적 추론 지원

	## Benchmark

	\| Benchmark \| Score \|
	\|---\|---\|
	\| CLIcK (Korean Cultural & Linguistic Knowledge) \| 81.0% \|
	\| KMMLU-Pro (Korean MMLU Professional) \| 74.0% \|

	## Model Specifications

	\| Property \| Value \|
	\|---\|---\|
	\| Architecture \| Qwen3.5 Hybrid (GatedDeltaNet + Attention, 64 layers) \|
	\| Parameters \| ~27B \|
	\| Hidden Size \| 5120 \|
	\| Intermediate Size \| 16384 \|
	\| Context Length \| 262,144 tokens \|
	\| Precision \| BF16 \|
	\| Vocab Size \| 248,320 \|
	\| Thinking \| Supported (`<think>` tags) \|
	\| License \| Apache 2.0 \|

	## Usage

	> Requirements: `transformers >= 5.5.4`

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	model = AutoModelForCausalLM.from_pretrained(
	"Anserwise/AWAXIS-Think-27b",
	torch_dtype=torch.bfloat16,
	device_map="auto",
	)
	tokenizer = AutoTokenizer.from_pretrained("Anserwise/AWAXIS-Think-27b")

	messages = [{"role": "user", "content": "조선시대의 과거제도에 대해 설명해주세요."}]
	text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	inputs = tokenizer(text, return_tensors="pt").to(model.device)
	outputs = model.generate(**inputs, max_new_tokens=1024, do_sample=False)
	print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
	```

	### vLLM

	```bash
	vllm serve Anserwise/AWAXIS-Think-27b \
	--enforce-eager \
	--max-model-len 32768 \
	--dtype bfloat16
	```

	## Features

	- Darwin-27B-Opus의 강력한 추론 능력 계승
	- 한국어 문화, 역사, 법률, 경제, 사회 등 한국 특화 지식 강화
	- Thinking mode를 통한 단계적 사고 추론
	- 다국어 지원 (한국어, 영어, 일본어, 중국어)
	- 262K 컨텍스트 길이 지원

	## Training

	\| Item \| Details \|
	\|---\|---\|
	\| Base Model \| [FINAL-Bench/Darwin-27B-Opus](https://huggingface.co/FINAL-Bench/Darwin-27B-Opus) \|
	\| Method \| Korean-specialized Supervised Fine-Tuning \|
	\| Data \| 한국어 문화·지식 중심 고품질 instruction 데이터 \|
	\| Developer \| [Anserwise](https://huggingface.co/Anserwise) \|

	## Acknowledgements

	- [FINAL-Bench](https://huggingface.co/FINAL-Bench) — Darwin-27B-Opus base model
	- [Qwen Team](https://huggingface.co/Qwen) — Qwen3.5 architecture