Instructions to use researchaudio/Qwen2.5-7B-CodeSoup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use researchaudio/Qwen2.5-7B-CodeSoup with Transformers:

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

pipe = pipeline("text-generation", model="researchaudio/Qwen2.5-7B-CodeSoup")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("researchaudio/Qwen2.5-7B-CodeSoup")
model = AutoModelForCausalLM.from_pretrained("researchaudio/Qwen2.5-7B-CodeSoup")
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 researchaudio/Qwen2.5-7B-CodeSoup with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "researchaudio/Qwen2.5-7B-CodeSoup"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "researchaudio/Qwen2.5-7B-CodeSoup",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/researchaudio/Qwen2.5-7B-CodeSoup

SGLang

How to use researchaudio/Qwen2.5-7B-CodeSoup 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 "researchaudio/Qwen2.5-7B-CodeSoup" \
    --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": "researchaudio/Qwen2.5-7B-CodeSoup",
		"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 "researchaudio/Qwen2.5-7B-CodeSoup" \
        --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": "researchaudio/Qwen2.5-7B-CodeSoup",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use researchaudio/Qwen2.5-7B-CodeSoup with Docker Model Runner:
```
docker model run hf.co/researchaudio/Qwen2.5-7B-CodeSoup
```

Qwen2.5-7B-CodeSoup

🍲 Model Soup created using weighted averaging based on Meta's Souper-Model.

Weights

coder: 60%
general: 40%

Expected Performance (Linear Prediction)

Benchmark	Predicted Score
GSM8K	70.4%
HumanEval	81.1%

Note: Actual performance may differ due to weight interference effects.

Component Models

Model	GSM8K	HumanEval
Qwen2.5-7B-Instruct	85.4%	70.1%
Qwen2.5-Coder-7B-Instruct	60.4%	88.4%
Qwen2.5-Math-7B-Instruct	90.3%	52.4%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("researchaudio/Qwen2.5-7B-CodeSoup")
tokenizer = AutoTokenizer.from_pretrained("researchaudio/Qwen2.5-7B-CodeSoup")

messages = [{"role": "user", "content": "Solve: What is 15% of 80?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))

Citation

@misc{soupermodel2025,
    title={Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance},
    author={Shalini Maiti and others},
    year={2025},
    url={https://arxiv.org/abs/2511.13254},
}

Downloads last month: 2

Model tree for researchaudio/Qwen2.5-7B-CodeSoup

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(3301)

this model

Paper for researchaudio/Qwen2.5-7B-CodeSoup

Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance

Paper • 2511.13254 • Published Nov 17, 2025 • 140