Instructions to use You3dimgeo/cycleqd-qwen25-7b-math-alpha020 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use You3dimgeo/cycleqd-qwen25-7b-math-alpha020 with Transformers:

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

pipe = pipeline("text-generation", model="You3dimgeo/cycleqd-qwen25-7b-math-alpha020")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("You3dimgeo/cycleqd-qwen25-7b-math-alpha020")
model = AutoModelForCausalLM.from_pretrained("You3dimgeo/cycleqd-qwen25-7b-math-alpha020")
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

vLLM

How to use You3dimgeo/cycleqd-qwen25-7b-math-alpha020 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "You3dimgeo/cycleqd-qwen25-7b-math-alpha020"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "You3dimgeo/cycleqd-qwen25-7b-math-alpha020",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/You3dimgeo/cycleqd-qwen25-7b-math-alpha020

SGLang

How to use You3dimgeo/cycleqd-qwen25-7b-math-alpha020 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 "You3dimgeo/cycleqd-qwen25-7b-math-alpha020" \
    --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": "You3dimgeo/cycleqd-qwen25-7b-math-alpha020",
		"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 "You3dimgeo/cycleqd-qwen25-7b-math-alpha020" \
        --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": "You3dimgeo/cycleqd-qwen25-7b-math-alpha020",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use You3dimgeo/cycleqd-qwen25-7b-math-alpha020 with Docker Model Runner:
```
docker model run hf.co/You3dimgeo/cycleqd-qwen25-7b-math-alpha020
```

CycleQD Qwen2.5-7B Math α=0.20

This model is a CycleQD-merged version of Qwen2.5-7B, specifically tuned for mathematical reasoning tasks.

Model Details

Base Models: Qwen2.5-7B and Qwen2.5-7B-Instruct
Merge Method: Linear interpolation with α=0.20
Formula: (1-0.20) × Qwen2.5-7B + 0.20 × Qwen2.5-7B-Instruct
Created: August 14, 2025
Model Size: 7B parameters (~15GB)

Performance

This model achieved significant improvement on the HLE Math evaluation:

Accuracy: 14.29% (5/35 questions correct)
Improvement: 5x improvement from baseline (1/35 → 5/35)
Evaluation: HLE Math category
Judge Model: Qwen2.5-32B-Instruct

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("You3dimgeo/cycleqd-qwen25-7b-math-alpha020")
tokenizer = AutoTokenizer.from_pretrained("You3dimgeo/cycleqd-qwen25-7b-math-alpha020")

# Use for mathematical reasoning
prompt = "Solve the equation: 2x^2 + 5x - 3 = 0"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200)
print(tokenizer.decode(outputs[0]))

Training/Merge Details

This model was created using the CycleQD (Cycle Quality-Diversity) approach:

Started with Qwen2.5-7B base model
Applied CycleQD optimization for mathematical reasoning
Merged with instruction-tuned variant using α=0.20
Evaluated on HLE Math benchmark

License

This model is licensed under Apache 2.0, following the original Qwen2.5 license.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for You3dimgeo/cycleqd-qwen25-7b-math-alpha020

Qwen/Qwen2.5-7B

Qwen/Qwen2.5-7B-Instruct

Merge model

this model

Evaluation results

accuracy on HLE Math
self-reported

14.290