Instructions to use hutaobentao/furina-qwen3.6-27b-merged-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hutaobentao/furina-qwen3.6-27b-merged-2.0 with Transformers:

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

pipe = pipeline("image-text-to-text", model="hutaobentao/furina-qwen3.6-27b-merged-2.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hutaobentao/furina-qwen3.6-27b-merged-2.0")
model = AutoModelForCausalLM.from_pretrained("hutaobentao/furina-qwen3.6-27b-merged-2.0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hutaobentao/furina-qwen3.6-27b-merged-2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hutaobentao/furina-qwen3.6-27b-merged-2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hutaobentao/furina-qwen3.6-27b-merged-2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hutaobentao/furina-qwen3.6-27b-merged-2.0

SGLang

How to use hutaobentao/furina-qwen3.6-27b-merged-2.0 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 "hutaobentao/furina-qwen3.6-27b-merged-2.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hutaobentao/furina-qwen3.6-27b-merged-2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "hutaobentao/furina-qwen3.6-27b-merged-2.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hutaobentao/furina-qwen3.6-27b-merged-2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hutaobentao/furina-qwen3.6-27b-merged-2.0 with Docker Model Runner:
```
docker model run hf.co/hutaobentao/furina-qwen3.6-27b-merged-2.0
```

HuTaoDeDog/furina-qwen3.6-27b-merged-2.0

对该模型有疑问，请在Modelscope中国大陆站（modelscope.cn）平台搜索用户名为HuTaoDeDog的用户提issue，hf这里不一定有时间看。 If you have any questions about the model,please contact me(My username is HuTaoDeDog)on Modelscope China Platform(modelscope.cn).

模型特性

塞了一整段的提示词和数据集来进行角色扮演，不过可能会比较机械，因为这是27b小模型。

关于量化

它永远只能是这样；我没有量化需要的硬件，我也没钱，这个模型甚至就用的是modelscope的notebook调的。如果你要是闲的没事干，也可以去量化一下，反正开源了

基底模型

基于Qwen3.6-27b微调原地址

Downloads last month: -

Safetensors

Model size

27B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for hutaobentao/furina-qwen3.6-27b-merged-2.0

Base model

Qwen/Qwen3.6-27B

Finetuned

(341)

this model