Instructions to use FINGU-AI/QwQ-Buddy-32B-Alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINGU-AI/QwQ-Buddy-32B-Alpha with Transformers:

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

pipe = pipeline("text-generation", model="FINGU-AI/QwQ-Buddy-32B-Alpha")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FINGU-AI/QwQ-Buddy-32B-Alpha")
model = AutoModelForCausalLM.from_pretrained("FINGU-AI/QwQ-Buddy-32B-Alpha", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FINGU-AI/QwQ-Buddy-32B-Alpha with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FINGU-AI/QwQ-Buddy-32B-Alpha

SGLang

How to use FINGU-AI/QwQ-Buddy-32B-Alpha 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 "FINGU-AI/QwQ-Buddy-32B-Alpha" \
    --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": "FINGU-AI/QwQ-Buddy-32B-Alpha",
		"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 "FINGU-AI/QwQ-Buddy-32B-Alpha" \
        --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": "FINGU-AI/QwQ-Buddy-32B-Alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINGU-AI/QwQ-Buddy-32B-Alpha with Docker Model Runner:
```
docker model run hf.co/FINGU-AI/QwQ-Buddy-32B-Alpha
```

QwQ-Buddy-32B-Alpha

Model Summary

QwQ-Buddy-32B-Alpha is a merged 32B model created by fusing two high-performing models:

huihui-ai/QwQ-32B-Coder-Fusion-9010 (strong in coding and logical reasoning)
OpenBuddy/openbuddy-qwq-32b-v24.2-200k (strong in general knowledge and reasoning)

The merge was performed using Spherical Linear Interpolation (SLERP) to ensure a smooth and balanced integration of capabilities from both source models. The result is a powerful and versatile 32B model that excels in both coding and reasoning tasks, making it one of the top candidates for leaderboard evaluations.

Model Details

Model Type: Merged LLM (Qwen-2.5 32B architecture-based)
Precision: bfloat16
Merge Method: SLERP (Spherical Linear Interpolation)
Weight Type: Original (fully merged model, NOT delta-based)
Context Length: 200K tokens (inherits capabilities from OpenBuddy-QwQ)
Training Base Models:
- huihui-ai/QwQ-32B-Coder-Fusion-9010
- OpenBuddy/openbuddy-qwq-32b-v24.2-200k
Merged Layers:
- 0-32 equally distributed from both models
- 24-64 optimized for knowledge reasoning and logical computations

Performance Improvements

✅ Stronger coding capabilities (inherits high performance from QwQ-32B-Coder-Fusion-9010) ✅ Enhanced general knowledge & reasoning (boosted by OpenBuddy-QwQ) ✅ Balanced self-attention and MLP layers for smoother response generation ✅ Higher robustness in multilingual support (OpenBuddy-QwQ contributions) ✅ Fine-tuned SLERP weighting for best accuracy in benchmarks

Expected Leaderboard Performance

Based on internal testing and model comparisons, QwQ-Buddy-32B-Alpha is expected to achieve top 20 rankings in:

HumanEval (coding tasks)
MMLU (multi-task language understanding)
HellaSwag (commonsense reasoning)
BBH (Big Bench Hard) (complex problem-solving)

Limitations & Considerations

🚧 Not fine-tuned post-merge (raw merge evaluation may have slight instabilities)
🚧 No explicit safety alignment applied (inherits behavior from base models)
🚧 Performance on unseen edge cases requires additional evaluation

How to Use

To load the model for inference:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "FINGU-AI/QwQ-Buddy-32B-Alpha"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="bfloat16")

inputs = tokenizer("Write a Python function to compute Fibonacci numbers:", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0]))

Acknowledgments

This model was built using:

MergeKit for SLERP-based weight interpolation
Hugging Face Transformers for model loading and testing
Leaderboard Evaluation Benchmarks for performance comparisons

Contact & Feedback

For any inquiries, issues, or feedback regarding QwQ-Buddy-32B-Alpha, please reach out via GitHub or Hugging Face discussions.

Downloads last month: 4

Safetensors

Model size

38B params

Tensor type

F16

F32