Instructions to use HAD653/qwen3-1.7b-magistral-math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HAD653/qwen3-1.7b-magistral-math with Transformers:

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

pipe = pipeline("text-generation", model="HAD653/qwen3-1.7b-magistral-math")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HAD653/qwen3-1.7b-magistral-math")
model = AutoModelForCausalLM.from_pretrained("HAD653/qwen3-1.7b-magistral-math", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HAD653/qwen3-1.7b-magistral-math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HAD653/qwen3-1.7b-magistral-math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HAD653/qwen3-1.7b-magistral-math",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HAD653/qwen3-1.7b-magistral-math

SGLang

How to use HAD653/qwen3-1.7b-magistral-math 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 "HAD653/qwen3-1.7b-magistral-math" \
    --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": "HAD653/qwen3-1.7b-magistral-math",
		"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 "HAD653/qwen3-1.7b-magistral-math" \
        --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": "HAD653/qwen3-1.7b-magistral-math",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use HAD653/qwen3-1.7b-magistral-math with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HAD653/qwen3-1.7b-magistral-math to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HAD653/qwen3-1.7b-magistral-math to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HAD653/qwen3-1.7b-magistral-math to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="HAD653/qwen3-1.7b-magistral-math",
    max_seq_length=2048,
)

Docker Model Runner
How to use HAD653/qwen3-1.7b-magistral-math with Docker Model Runner:
```
docker model run hf.co/HAD653/qwen3-1.7b-magistral-math
```

HAD653 commited on Dec 4, 2025

Commit

9d5ff09

verified ·

1 Parent(s): b6a795c

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ tags:
 - bfloat16
 base_model: unsloth/Qwen3-1.7B-Base
 datasets:
-- HAD653/GSM8K-OpenMath-Magistral-13k
 pipeline_tag: text-generation
 library_name: transformers
 ---
@@ -291,6 +291,6 @@ If you use this model in your work, please cite:
   title        = {Qwen3-1.7B Magistral Math: A 1.7B Math Reasoning Model with Magistral Chain-of-Thought},
   year         = {2025},
   howpublished = {\url{https://huggingface.co/HAD653/qwen3-1.7b-magistral-math}},
-  note         = {Fine-tuned on GSM8K + OpenMath Magistral 13k with full BF16 supervision.}
 }
 ```

 - bfloat16
 base_model: unsloth/Qwen3-1.7B-Base
 datasets:
+- HAD653/GSM8K-OpenMath-MathReason-13k
 pipeline_tag: text-generation
 library_name: transformers
 ---
   title        = {Qwen3-1.7B Magistral Math: A 1.7B Math Reasoning Model with Magistral Chain-of-Thought},
   year         = {2025},
   howpublished = {\url{https://huggingface.co/HAD653/qwen3-1.7b-magistral-math}},
+  note         = {Fine-tuned on GSM8K + OpenMath MathReason 13k with full BF16 supervision.}
 }
 ```