Instructions to use huihui-ai/QwQ-32B-Coder-Fusion-9010 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huihui-ai/QwQ-32B-Coder-Fusion-9010 with Transformers:

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

pipe = pipeline("text-generation", model="huihui-ai/QwQ-32B-Coder-Fusion-9010")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huihui-ai/QwQ-32B-Coder-Fusion-9010")
model = AutoModelForCausalLM.from_pretrained("huihui-ai/QwQ-32B-Coder-Fusion-9010")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huihui-ai/QwQ-32B-Coder-Fusion-9010 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huihui-ai/QwQ-32B-Coder-Fusion-9010"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huihui-ai/QwQ-32B-Coder-Fusion-9010",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/huihui-ai/QwQ-32B-Coder-Fusion-9010

SGLang

How to use huihui-ai/QwQ-32B-Coder-Fusion-9010 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 "huihui-ai/QwQ-32B-Coder-Fusion-9010" \
    --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": "huihui-ai/QwQ-32B-Coder-Fusion-9010",
		"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 "huihui-ai/QwQ-32B-Coder-Fusion-9010" \
        --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": "huihui-ai/QwQ-32B-Coder-Fusion-9010",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use huihui-ai/QwQ-32B-Coder-Fusion-9010 with Docker Model Runner:
```
docker model run hf.co/huihui-ai/QwQ-32B-Coder-Fusion-9010
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

huihui-ai/QwQ-32B-Coder-Fusion-9010

Overview

QwQ-32B-Coder-Fusion-9010 is a mixed model that combines the strengths of two powerful Qwen-based models: huihui-ai/QwQ-32B-Preview-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.
The weights are blended in a 9:1 ratio, with 90% of the weights from the abliterated QwQ-32B-Preview-abliterated and 10% from the abliterated Qwen2.5-Coder-32B-Instruct-abliterated model. Although it's a simple mix, the model is usable, and no gibberish has appeared. This is an experiment. I test the 9:1, 8:2, and 7:3 ratios separately to see how much impact they have on the model.
Now the effective ratios are 9:1, 8:2, and 7:3. Any other ratios (6:4,5:5) would result in mixed or unclear expressions.

Please refer to the mixed source code.

Model Details

Base Models:
- huihui-ai/QwQ-32B-Preview-abliterated (90%)
- huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated (10%)
Model Size: 32B parameters
Architecture: Qwen 2.5
Mixing Ratio: 9:1 (QwQ-32B-Preview-abliterated:Qwen2.5-Coder-32B-Instruct-abliterated)