Instructions to use kaushik-harsh-99/SmolLM-135M-Maths-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaushik-harsh-99/SmolLM-135M-Maths-SFT with Transformers:

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

pipe = pipeline("text-generation", model="kaushik-harsh-99/SmolLM-135M-Maths-SFT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kaushik-harsh-99/SmolLM-135M-Maths-SFT")
model = AutoModelForCausalLM.from_pretrained("kaushik-harsh-99/SmolLM-135M-Maths-SFT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kaushik-harsh-99/SmolLM-135M-Maths-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaushik-harsh-99/SmolLM-135M-Maths-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaushik-harsh-99/SmolLM-135M-Maths-SFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kaushik-harsh-99/SmolLM-135M-Maths-SFT

SGLang

How to use kaushik-harsh-99/SmolLM-135M-Maths-SFT 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 "kaushik-harsh-99/SmolLM-135M-Maths-SFT" \
    --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": "kaushik-harsh-99/SmolLM-135M-Maths-SFT",
		"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 "kaushik-harsh-99/SmolLM-135M-Maths-SFT" \
        --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": "kaushik-harsh-99/SmolLM-135M-Maths-SFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use kaushik-harsh-99/SmolLM-135M-Maths-SFT with Docker Model Runner:
```
docker model run hf.co/kaushik-harsh-99/SmolLM-135M-Maths-SFT
```

SmolLM-135M-Math-SFT

A 135M parameter mathematical reasoning model obtained by supervised fine-tuning Unsloth's SmolLM-135M on a curated mathematical instruction dataset.

This checkpoint is the first stage of a larger alignment pipeline:

Base Model → Math SFT → Reinforcement Learning (GRPO/RL) → Final Model

The goal is to investigate how much reasoning ability can be extracted from a very small language model before applying reinforcement learning.

Base Model

Model: unsloth/SmolLM-135M
Architecture: SmolLM (Decoder-only Transformer)
Parameters: 135M

Base model: https://huggingface.co/unsloth/SmolLM-135M

Training

This model was supervised fine-tuned on mathematical instruction-following data to improve:

Arithmetic
Algebra
Multi-step reasoning
Mathematical explanations
Instruction following

This checkpoint contains only the SFT stage.

The next stage will further optimize reasoning through reinforcement learning.

Roadmap

✅ Base model
✅ Supervised Fine-Tuning (this release)
⏳ Reinforcement Learning (GRPO)
⏳ Evaluation on standard reasoning benchmarks
⏳ Final release

Acknowledgements

This work is built upon the excellent Unsloth SmolLM-135M base model developed by the Unsloth team.

Downloads last month: 43

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for kaushik-harsh-99/SmolLM-135M-Maths-SFT

Base model

HuggingFaceTB/SmolLM-135M

Finetuned

unsloth/SmolLM-135M

Quantized

(5)

this model