Instructions to use feeltheAGI/Maverick-Math-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use feeltheAGI/Maverick-Math-7B with Transformers:

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

pipe = pipeline("text-generation", model="feeltheAGI/Maverick-Math-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("feeltheAGI/Maverick-Math-7B")
model = AutoModelForCausalLM.from_pretrained("feeltheAGI/Maverick-Math-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use feeltheAGI/Maverick-Math-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/feeltheAGI/Maverick-Math-7B

SGLang

How to use feeltheAGI/Maverick-Math-7B 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 "feeltheAGI/Maverick-Math-7B" \
    --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": "feeltheAGI/Maverick-Math-7B",
		"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 "feeltheAGI/Maverick-Math-7B" \
        --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": "feeltheAGI/Maverick-Math-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Maverick-Math-7B

Model description

Maverick-Math is a Mistral Fine-tune, on top of math and code datasets and performs very well on benchmarks .

🏆 Evaluation

gsm8k

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
gsm8k	3	strict-match	5	exact_match	0.7331	±	0.0122
		flexible-extract	5	exact_match	0.7400	±	0.0121

mathqa

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
mathqa	1	none	None	acc	0.3591	±	0.0088
		none	None	acc_norm	0.3635	±	0.0088

Downloads last month: 802

Model tree for feeltheAGI/Maverick-Math-7B

Quantizations

2 models

feeltheAGI
/

Maverick-Math-7B