Instructions to use project-numina/NuminaMath-7B-TIR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use project-numina/NuminaMath-7B-TIR with Transformers:

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

pipe = pipeline("text-generation", model="project-numina/NuminaMath-7B-TIR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("project-numina/NuminaMath-7B-TIR")
model = AutoModelForCausalLM.from_pretrained("project-numina/NuminaMath-7B-TIR", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use project-numina/NuminaMath-7B-TIR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "project-numina/NuminaMath-7B-TIR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "project-numina/NuminaMath-7B-TIR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/project-numina/NuminaMath-7B-TIR

SGLang

How to use project-numina/NuminaMath-7B-TIR 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 "project-numina/NuminaMath-7B-TIR" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "project-numina/NuminaMath-7B-TIR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "project-numina/NuminaMath-7B-TIR" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "project-numina/NuminaMath-7B-TIR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use project-numina/NuminaMath-7B-TIR with Docker Model Runner:
```
docker model run hf.co/project-numina/NuminaMath-7B-TIR
```

NuminaMath-7B-TIR

Commit History

Jul 21, 2025

08:23
add AIBOM⁠

RiccardoDav

Verified signature
9560cf7

Aug 14, 2024

14:05
add results table (#7)⁠

lewtun +1: benlipkin HF Staff

Verified signature
cf2aaf3

Jul 19, 2024

12:10
Update config.json

lewtun HF Staff

Verified signature
8a0609f
12:10
Update README.md (#6)⁠

lewtun HF Staff

Verified signature
ced8eac
12:08
Upload LlamaForCausalLM

lewtun HF Staff

Verified signature
e94e299

Jul 11, 2024

11:41
Improve widget example (#2)⁠

lewtun +1: osanseviero HF Staff

Verified signature
8444f4a
08:50
Update README.md

lewtun HF Staff

Verified signature
c69996e

Jul 10, 2024

15:23
Add citation (#1)⁠

liyongsea +1: lewtun

Verified signature
c6e394c
12:45
Update README.md

lewtun HF Staff

Verified signature
a0eecf7

Jul 9, 2024

21:36
Update README.md

lewtun HF Staff

Verified signature
03dee68

Jul 8, 2024

15:03
Update README.md

lewtun HF Staff

Verified signature
5923b90
15:02
Update README.md

lewtun HF Staff

Verified signature
6467693
15:00
Update README.md

lewtun HF Staff

Verified signature
005033e
14:47
Update README

lewtun HF Staff

29e5192
14:09
Upload thumbnail.png

lewtun HF Staff

Verified signature
7353400
07:39
Update README.md

edbeeching HF Staff

Verified signature
034463f
07:30
Update README.md

edbeeching HF Staff

Verified signature
423db84
07:29
Update README.md

edbeeching HF Staff

Verified signature
d3eacdc

Jul 5, 2024

13:04
Update README.md

edbeeching HF Staff

Verified signature
f668db3
12:00
Update README.md

edbeeching HF Staff

Verified signature
f49478d
11:59
Update README.md

edbeeching HF Staff

Verified signature
7027b1c
08:27
Update README.md

edbeeching HF Staff

Verified signature
f66744c

Jul 4, 2024

09:29
Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint

lewtun HF Staff

Verified signature
167ee6b
09:28
initial commit

lewtun HF Staff

Verified signature
67c0635

Commit History

Jul 21, 2025

add AIBOM⁠

Aug 14, 2024

add results table (#7)⁠

Jul 19, 2024

Update config.json

Update README.md (#6)⁠

Upload LlamaForCausalLM

Jul 11, 2024

Improve widget example (#2)⁠

Update README.md

Jul 10, 2024

Add citation (#1)⁠

Update README.md

Jul 9, 2024

Update README.md

Jul 8, 2024

Update README.md

Update README.md

Update README.md

Update README

Upload thumbnail.png

Update README.md

Update README.md

Update README.md

Jul 5, 2024

Update README.md

Update README.md

Update README.md

Update README.md

Jul 4, 2024

Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint

initial commit