Instructions to use When-Does-Reasoning-Matter/Qwen2.5-3B-ift with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use When-Does-Reasoning-Matter/Qwen2.5-3B-ift with Transformers:

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

pipe = pipeline("text-generation", model="When-Does-Reasoning-Matter/Qwen2.5-3B-ift")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("When-Does-Reasoning-Matter/Qwen2.5-3B-ift")
model = AutoModelForMultimodalLM.from_pretrained("When-Does-Reasoning-Matter/Qwen2.5-3B-ift")
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 When-Does-Reasoning-Matter/Qwen2.5-3B-ift with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "When-Does-Reasoning-Matter/Qwen2.5-3B-ift"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "When-Does-Reasoning-Matter/Qwen2.5-3B-ift",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/When-Does-Reasoning-Matter/Qwen2.5-3B-ift

SGLang

How to use When-Does-Reasoning-Matter/Qwen2.5-3B-ift 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 "When-Does-Reasoning-Matter/Qwen2.5-3B-ift" \
    --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": "When-Does-Reasoning-Matter/Qwen2.5-3B-ift",
		"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 "When-Does-Reasoning-Matter/Qwen2.5-3B-ift" \
        --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": "When-Does-Reasoning-Matter/Qwen2.5-3B-ift",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use When-Does-Reasoning-Matter/Qwen2.5-3B-ift with Docker Model Runner:
```
docker model run hf.co/When-Does-Reasoning-Matter/Qwen2.5-3B-ift
```

When Does Reasoning Matter?

Dataset Icon

This model was trained as part of the paper When Does Reasoning Matter? It belongs to a collection of General and Math-specific student models distilled from Instruction-Fine-Tuned (IFT) or Reasoning answers generated by Qwen/Qwen3-235B-A22B.

Datasets

These models were trained on the largest set of IFT and Reasoning answer pairs:

General dataset: general-reasoning-ift-pairs
Math dataset: math-reasoning-ift-pairs

Available Models

General		Math
IFT Models	Reasoning Models	IFT Models	Reasoning Models
Qwen2.5-0.5B-ift	Qwen2.5-0.5B-reasoning	Qwen2.5-0.5B-math-ift	Qwen2.5-0.5B-math-reasoning
Qwen2.5-1.5B-ift	Qwen2.5-1.5B-reasoning	Qwen2.5-1.5B-math-ift	Qwen2.5-1.5B-math-reasoning
Qwen2.5-3B-ift	Qwen2.5-3B-reasoning	Qwen2.5-3B-math-ift	Qwen2.5-3B-math-reasoning
Qwen2.5-7B-ift	Qwen2.5-7B-reasoning	Qwen2.5-7B-math-ift	Qwen2.5-7B-math-reasoning
Qwen2.5-14B-ift	Qwen2.5-14B-reasoning	Qwen2.5-14B-math-ift	Qwen2.5-14B-math-reasoning

If you use this dataset in your work, please cite: When Does Reasoning Matter?

@misc{boizard2025doesreasoningmattercontrolled,
      title={When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance}, 
      author={Nicolas Boizard and Hippolyte Gisserot-Boukhlef and Kevin El-Haddad and Céline Hudelot and Pierre Colombo},
      year={2025},
      eprint={2509.22193},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2509.22193}, 
}

Downloads last month: 4

Safetensors

Model size

242k params

Tensor type

BF16

Datasets used to train When-Does-Reasoning-Matter/Qwen2.5-3B-ift

Collection including When-Does-Reasoning-Matter/Qwen2.5-3B-ift

IFT

Collection

12 items • Updated Sep 26, 2025

Paper for When-Does-Reasoning-Matter/Qwen2.5-3B-ift

When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance

Paper • 2509.22193 • Published Sep 26, 2025 • 38