Instructions to use SkyAsl/Qwen-3-4B-Math_Solver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SkyAsl/Qwen-3-4B-Math_Solver with Transformers:

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

pipe = pipeline("text-generation", model="SkyAsl/Qwen-3-4B-Math_Solver")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SkyAsl/Qwen-3-4B-Math_Solver", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SkyAsl/Qwen-3-4B-Math_Solver with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SkyAsl/Qwen-3-4B-Math_Solver"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SkyAsl/Qwen-3-4B-Math_Solver",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SkyAsl/Qwen-3-4B-Math_Solver

SGLang

How to use SkyAsl/Qwen-3-4B-Math_Solver 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 "SkyAsl/Qwen-3-4B-Math_Solver" \
    --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": "SkyAsl/Qwen-3-4B-Math_Solver",
		"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 "SkyAsl/Qwen-3-4B-Math_Solver" \
        --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": "SkyAsl/Qwen-3-4B-Math_Solver",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SkyAsl/Qwen-3-4B-Math_Solver with Docker Model Runner:
```
docker model run hf.co/SkyAsl/Qwen-3-4B-Math_Solver
```

Model Card for Model ID

Training Data

https://huggingface.co/datasets/meta-math/MetaMathQA

Training Hyperparameters

batch_size = 8, epoch = 1, learning_rate = 1e-4

Lora: r=16, lora_alpha=32, lora_dropout=0.05

Metrics

metrics={'train_runtime': 729.5559, 'train_samples_per_second': 9.746, 'train_steps_per_second': 0.306, 'total_flos': 7.949170591137792e+16, 'train_loss': 2.817356810976037, 'epoch': 1.0}

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for SkyAsl/Qwen-3-4B-Math_Solver

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

(1077)

this model

SkyAsl
/

Qwen-3-4B-Math_Solver

Model Card for Model ID

Training Data

Training Hyperparameters

Metrics

Model tree for SkyAsl/Qwen-3-4B-Math_Solver

Dataset used to train SkyAsl/Qwen-3-4B-Math_Solver