Instructions to use meta-math/MetaMath-Mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-math/MetaMath-Mistral-7B with Transformers:

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

pipe = pipeline("text-generation", model="meta-math/MetaMath-Mistral-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-math/MetaMath-Mistral-7B")
model = AutoModelForCausalLM.from_pretrained("meta-math/MetaMath-Mistral-7B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use meta-math/MetaMath-Mistral-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/meta-math/MetaMath-Mistral-7B

SGLang

How to use meta-math/MetaMath-Mistral-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 "meta-math/MetaMath-Mistral-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": "meta-math/MetaMath-Mistral-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 "meta-math/MetaMath-Mistral-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": "meta-math/MetaMath-Mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use meta-math/MetaMath-Mistral-7B with Docker Model Runner:
```
docker model run hf.co/meta-math/MetaMath-Mistral-7B
```

Longhui98 commited on Oct 22, 2023

Commit

92d3c60

1 Parent(s): 4129895

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ https://meta-math.github.io/
 ## Model Details
-MetaMath-Mistral-7B is fully fine-tuned on the MetaMathQA datasets and based on the very strong Mistral-7B model. It is glad to see using MetaMathQA datasets and change the base model from llama-2-7B to Mistral-7b can boost the GSM8K performance from 66.5 to **77.7**.
 To fine-tune Mistral-7B, I would suggest using a smaller learning rate (usually 1/5 to 1/10 of the lr for LlaMa-2-7B) and staying other training args unchanged.
 More training details and scripts can be seen at https://github.com/meta-math/MetaMath

 ## Model Details
+MetaMath-Mistral-7B is fully fine-tuned on the MetaMathQA datasets and based on the powerful Mistral-7B model. It is glad to see using MetaMathQA datasets and change the base model from llama-2-7B to Mistral-7b can boost the GSM8K performance from 66.5 to **77.7**.
 To fine-tune Mistral-7B, I would suggest using a smaller learning rate (usually 1/5 to 1/10 of the lr for LlaMa-2-7B) and staying other training args unchanged.
 More training details and scripts can be seen at https://github.com/meta-math/MetaMath