Instructions to use modrill/math-think-s1-qwen3-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/math-think-s1-qwen3-4b with Transformers:

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

pipe = pipeline("text-generation", model="modrill/math-think-s1-qwen3-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("modrill/math-think-s1-qwen3-4b")
model = AutoModelForMultimodalLM.from_pretrained("modrill/math-think-s1-qwen3-4b")
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 modrill/math-think-s1-qwen3-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/math-think-s1-qwen3-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/math-think-s1-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/math-think-s1-qwen3-4b

SGLang

How to use modrill/math-think-s1-qwen3-4b 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 "modrill/math-think-s1-qwen3-4b" \
    --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": "modrill/math-think-s1-qwen3-4b",
		"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 "modrill/math-think-s1-qwen3-4b" \
        --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": "modrill/math-think-s1-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modrill/math-think-s1-qwen3-4b with Docker Model Runner:
```
docker model run hf.co/modrill/math-think-s1-qwen3-4b
```

math_think_s1

Full-parameter SFT of Qwen3-4B-Base for math reasoning with explicit thinking blocks (qwen3 template + enable_thinking: true).

Base model

Qwen/Qwen3-4B-Base

Training data

Dataset: math_think_s1 — 75,905 ShareGPT samples
Source: qihoo360/Light-R1-SFTData (stage1-76k.json)
Decontamination: MinHash + numeric normalization vs AIME/MATH eval prompts (1 sample removed)

Training recipe

Item	Value
Framework	LLaMA-Factory
Method	Full SFT, DeepSpeed ZeRO-3
Template	`qwen3` (reasoning / thinking)
Cutoff	32768
Packing	true
Epochs	4
LR	1e-5 (cosine, warmup 10%)
Batch	1 × 16 grad accum × 4 GPUs = 64
Steps	944
Train loss	0.6066
Runtime	~39.3 h

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "YOUR_HF_USERNAME/math-think-s1-qwen3-4b"  # replace after upload
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [{"role": "user", "content": "Find the sum of all positive integers n such that n^2 + 12n - 2007 is a perfect square."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)

Files

Release tarball includes: model.safetensors, config.json, generation_config.json, tokenizer files, chat_template.jinja, README.md, train_results.json, trainer_log.jsonl, MANIFEST.txt.

Downloads last month: 16

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for modrill/math-think-s1-qwen3-4b

Base model

Qwen/Qwen3-4B-Base

Finetuned

(322)

this model