Instructions to use gair-prox/Mistral-7B-ProXMath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gair-prox/Mistral-7B-ProXMath with Transformers:

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

pipe = pipeline("text-generation", model="gair-prox/Mistral-7B-ProXMath")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gair-prox/Mistral-7B-ProXMath")
model = AutoModelForCausalLM.from_pretrained("gair-prox/Mistral-7B-ProXMath")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gair-prox/Mistral-7B-ProXMath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gair-prox/Mistral-7B-ProXMath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gair-prox/Mistral-7B-ProXMath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gair-prox/Mistral-7B-ProXMath

SGLang

How to use gair-prox/Mistral-7B-ProXMath 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 "gair-prox/Mistral-7B-ProXMath" \
    --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": "gair-prox/Mistral-7B-ProXMath",
		"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 "gair-prox/Mistral-7B-ProXMath" \
        --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": "gair-prox/Mistral-7B-ProXMath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gair-prox/Mistral-7B-ProXMath with Docker Model Runner:
```
docker model run hf.co/gair-prox/Mistral-7B-ProXMath
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mistral-7B-ProXMath

ArXiv | Data: OpenWebMath-Pro | Code

Mistral-7B-ProXMath is a math-adapted Mistral-7B-v0.1 model that is continually pre-trained on OpenWebMath-Pro (a refined version by ProX) for 10B tokens.

Evaluations

ProX models are evaluated on 9 common math reasoning benchmarks.

Model	asdiv	gsm8k	mathqa	mawps	minerva_math	mmlu_stem	sat_math	svamp	tabmwp	average
Mistral-7B-v0.1	68.5	40.6	32.3	87.0	11.4	50.0	56.2	65.4	52.9	51.6
Mistral-7B-ProXMath	72.9	51.0	53.0	89.2	22.4	54.2	75.0	64.9	49.8	59.2

Citation

@article{zhou2024programming,
  title={Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale},
  author={Zhou, Fan and Wang, Zengzhi and Liu, Qian and Li, Junlong and Liu, Pengfei},
  journal={arXiv preprint arXiv:2409.17115},
  year={2024}
}