Instructions to use MathGenie/MathGenie-InterLM-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MathGenie/MathGenie-InterLM-20B with Transformers:

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

pipe = pipeline("text-generation", model="MathGenie/MathGenie-InterLM-20B", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MathGenie/MathGenie-InterLM-20B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MathGenie/MathGenie-InterLM-20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MathGenie/MathGenie-InterLM-20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MathGenie/MathGenie-InterLM-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MathGenie/MathGenie-InterLM-20B

SGLang

How to use MathGenie/MathGenie-InterLM-20B 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 "MathGenie/MathGenie-InterLM-20B" \
    --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": "MathGenie/MathGenie-InterLM-20B",
		"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 "MathGenie/MathGenie-InterLM-20B" \
        --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": "MathGenie/MathGenie-InterLM-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MathGenie/MathGenie-InterLM-20B with Docker Model Runner:
```
docker model run hf.co/MathGenie/MathGenie-InterLM-20B
```

MathGenieData

by mukaj - opened Apr 30, 2024

Discussion

mukaj

Apr 30, 2024

Can we get a release of the MathGenie dataset?

MathGenie

Owner May 4, 2024

Thank you for your interest in our work.

Regarding the dataset, we are currently communicating with administrators of the SenseTime company about legal issues, and we plan to release it upon the acceptence of our paper.

Please keep in touch and inform us if you have any other questions.

FrederikH

May 31, 2024

any update on a release of the dataset? would really like to play around with it

MathGenie

Owner Aug 11, 2024

Thank you for your interest in our work. The seed part of the data has already been released at MathGenie/MATH-GSM8K-Tool-81K. The full dataset will be released within the month.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment