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

Libraries

How to use AI-MO/NuminaMath-7B-TIR with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("AI-MO/NuminaMath-7B-TIR")
model = AutoModelForMultimodalLM.from_pretrained("AI-MO/NuminaMath-7B-TIR")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AI-MO/NuminaMath-7B-TIR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AI-MO/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": "AI-MO/NuminaMath-7B-TIR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AI-MO/NuminaMath-7B-TIR

SGLang

How to use AI-MO/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 "AI-MO/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": "AI-MO/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 "AI-MO/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": "AI-MO/NuminaMath-7B-TIR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

edbeeching HF Staff commited on Jul 8, 2024

Commit

d3eacdc

verified ·

1 Parent(s): f668db3

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -38,7 +38,7 @@ This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https:
 ## Model description
-- **Model type:** A 7B parameter Math model fine-tuned in two stages on Math Question answers and multi-step synthetic generations using tool integrated reasoning.
 - **Language(s) (NLP):** Primarily English
 - **License:** MIT
 - **Finetuned from model:** [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base)
@@ -86,7 +86,7 @@ exec(python_code)
 ## Bias, Risks, and Limitations
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
-Numina-Math-7B was create to solve math problems, the model has not been align to preferences beyond the domain of solving math, and should not be used in a general chat setting.
 ## Training procedure
@@ -126,7 +126,7 @@ The following hyperparameters were used during training:
 ## Citation
-If you find Numina-Math is useful in your work, please cite it with:
 ```
 @misc{beeching2024numina-math,

 ## Model description
+- **Model type:** A 7B parameter Math model fine-tuned in two stages of training, first on a dataset with 863k math question answer pairs and then on a dataset with 73k examples of multi-step synthetic generations using tool integrated reasoning.
 - **Language(s) (NLP):** Primarily English
 - **License:** MIT
 - **Finetuned from model:** [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base)
 ## Bias, Risks, and Limitations
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
+Numina-Math-7B was created to solve math problems, the model has not been aligned to preferences beyond the domain of solving math, and should not be used in a general chat setting.
 ## Training procedure
 ## Citation
+If you find Numina-Math useful in your work, please cite it with:
 ```
 @misc{beeching2024numina-math,