Instructions to use uf-aice-lab/math-roberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uf-aice-lab/math-roberta with Transformers:

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

pipe = pipeline("text-generation", model="uf-aice-lab/math-roberta")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("uf-aice-lab/math-roberta")
model = AutoModelForCausalLM.from_pretrained("uf-aice-lab/math-roberta", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use uf-aice-lab/math-roberta with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/uf-aice-lab/math-roberta

SGLang

How to use uf-aice-lab/math-roberta 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 "uf-aice-lab/math-roberta" \
    --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": "uf-aice-lab/math-roberta",
		"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 "uf-aice-lab/math-roberta" \
        --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": "uf-aice-lab/math-roberta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use uf-aice-lab/math-roberta with Docker Model Runner:
```
docker model run hf.co/uf-aice-lab/math-roberta
```

math-roberta

Commit History

Jan 25, 2025

14:54
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
f270d49

Nov 27, 2023

06:41
Corrected the model's config name so that it works properly (#2)⁠

uf-aice-lab +1: minhcrafters

52a12dd

Feb 11, 2022

20:21
Update model card

lichenglu

e535977

Feb 10, 2022

21:26
Merge branch 'main' of https://huggingface.co/uf-aice-lab/math_roberta

lichenglu

9273a34
18:53
Create README.md

uf-aice-lab

d0fa216
18:37
commit from chengluli

lichenglu

16a7a57
18:34
initial commit

system HF Staff

9489649

Commit History

Jan 25, 2025

Adding `safetensors` variant of this model⁠

Nov 27, 2023

Corrected the model's config name so that it works properly (#2)⁠

Feb 11, 2022

Update model card

Feb 10, 2022

Merge branch 'main' of https://huggingface.co/uf-aice-lab/math_roberta

Create README.md

commit from chengluli

initial commit