Instructions to use Pentium95/SmolLMathematician-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Pentium95/SmolLMathematician-3B with PEFT:
```
Task type is invalid.
```

How to use Pentium95/SmolLMathematician-3B with Transformers:

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

pipe = pipeline("text-generation", model="Pentium95/SmolLMathematician-3B")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Pentium95/SmolLMathematician-3B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Pentium95/SmolLMathematician-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pentium95/SmolLMathematician-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pentium95/SmolLMathematician-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Pentium95/SmolLMathematician-3B

SGLang

How to use Pentium95/SmolLMathematician-3B 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 "Pentium95/SmolLMathematician-3B" \
    --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": "Pentium95/SmolLMathematician-3B",
		"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 "Pentium95/SmolLMathematician-3B" \
        --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": "Pentium95/SmolLMathematician-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Pentium95/SmolLMathematician-3B with Docker Model Runner:
```
docker model run hf.co/Pentium95/SmolLMathematician-3B
```

Update README.md (Past Simple)

by qpqpqpqpqpqp - opened Oct 21, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ datasets:
 # Model Card for SmolLMathematician-3B
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B-Base](https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base).
-It has been trained using [TRL](https://github.com/huggingface/trl) on [TIGER-Lab/MathInstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct).
 Training Trackio:

 # Model Card for SmolLMathematician-3B
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B-Base](https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base).
+It was trained using [TRL](https://github.com/huggingface/trl) on [TIGER-Lab/MathInstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct).
 Training Trackio: