Instructions to use ShahriarFerdoush/llama-3.2-1b-math-solver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ShahriarFerdoush/llama-3.2-1b-math-solver with Transformers:

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

pipe = pipeline("text-generation", model="ShahriarFerdoush/llama-3.2-1b-math-solver")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ShahriarFerdoush/llama-3.2-1b-math-solver")
model = AutoModelForCausalLM.from_pretrained("ShahriarFerdoush/llama-3.2-1b-math-solver")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ShahriarFerdoush/llama-3.2-1b-math-solver with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ShahriarFerdoush/llama-3.2-1b-math-solver"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShahriarFerdoush/llama-3.2-1b-math-solver",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ShahriarFerdoush/llama-3.2-1b-math-solver

SGLang

How to use ShahriarFerdoush/llama-3.2-1b-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 "ShahriarFerdoush/llama-3.2-1b-math-solver" \
    --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": "ShahriarFerdoush/llama-3.2-1b-math-solver",
		"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 "ShahriarFerdoush/llama-3.2-1b-math-solver" \
        --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": "ShahriarFerdoush/llama-3.2-1b-math-solver",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ShahriarFerdoush/llama-3.2-1b-math-solver with Docker Model Runner:
```
docker model run hf.co/ShahriarFerdoush/llama-3.2-1b-math-solver
```

LLaMA-3.2-1B-Math (QLoRA)

Model Summary

LLaMA-3.2-1B-Math is a compact math-reasoning model fine-tuned from LLaMA 3.2-1B using 4-bit QLoRA. It is designed to study domain-specialized adaptation under strict compute limits.

Model Details

Base model: LLaMA 3.2-1B
Architecture: Decoder-only Transformer
Fine-tuning: QLoRA (4-bit NF4)
Training environment: Kaggle (single-GPU)

Datasets

Dataset	Purpose
GSM8K	Grade-school arithmetic reasoning
MATH	Competition-level mathematical problems

Datasets were processed into a plain-text format (no chat template) to match the base model.

Training Procedure

LoRA adapters inserted into attention and MLP projections
Mixed math datasets concatenated and split into train/eval
Optimized for stability on small batch sizes

Intended Use

Math reasoning benchmarks
Research on small-model specialization
Educational demonstrations of QLoRA fine-tuning

Out-of-Scope Uses

General chat or instruction following
Safety-critical or production systems

Known Limitations

Struggles with long proofs and symbolic manipulation
Sensitive to prompt phrasing
No RLHF or instruction tuning applied

Ethical Considerations

This model inherits biases and limitations from its base model and training data.

Acknowledgements

LLaMA (Meta)
GSM8K (OpenAI)
MATH (fdyrd/MATH)

Downloads last month: 3

Safetensors

Model size

1B params

Tensor type

F16