Instructions to use Neural-Hacker/Qwen3-Math-Reasoning-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neural-Hacker/Qwen3-Math-Reasoning-LoRA with Transformers:

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

pipe = pipeline("text-generation", model="Neural-Hacker/Qwen3-Math-Reasoning-LoRA")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Neural-Hacker/Qwen3-Math-Reasoning-LoRA", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Neural-Hacker/Qwen3-Math-Reasoning-LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neural-Hacker/Qwen3-Math-Reasoning-LoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neural-Hacker/Qwen3-Math-Reasoning-LoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Neural-Hacker/Qwen3-Math-Reasoning-LoRA

SGLang

How to use Neural-Hacker/Qwen3-Math-Reasoning-LoRA 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 "Neural-Hacker/Qwen3-Math-Reasoning-LoRA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neural-Hacker/Qwen3-Math-Reasoning-LoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Neural-Hacker/Qwen3-Math-Reasoning-LoRA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neural-Hacker/Qwen3-Math-Reasoning-LoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Neural-Hacker/Qwen3-Math-Reasoning-LoRA with Docker Model Runner:
```
docker model run hf.co/Neural-Hacker/Qwen3-Math-Reasoning-LoRA
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen3-Math-Reasoning-LoRA

A LoRA fine-tuned version of Qwen3-0.6B, trained on a math reasoning dataset (NVIDIA Math) to improve step-by-step problem-solving and numerical answer extraction.

Model Details

Base model: Qwen/Qwen3-0.6B

Fine-tuning: LoRA (Low-Rank Adaptation)

Task: Mathematical reasoning (percentages, geometry, arithmetic)

Dataset

nvidia/AceReason-Math

Hardware

AMD Instinct MI300X

Intended Use

Educational & research purposes

Math tutoring, reasoning and explanation generation

Not intended for high-stakes or safety-critical use.

License: cc-by-nc-4.0

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

Model tree for Neural-Hacker/Qwen3-Math-Reasoning-LoRA

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Adapter

(401)

this model

Neural-Hacker
/

Qwen3-Math-Reasoning-LoRA

You need to agree to share your contact information to access this model

Model tree for Neural-Hacker/Qwen3-Math-Reasoning-LoRA

Dataset used to train Neural-Hacker/Qwen3-Math-Reasoning-LoRA