Instructions to use MathLLMs/MathCoder-L-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MathLLMs/MathCoder-L-13B with Transformers:

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

pipe = pipeline("text-generation", model="MathLLMs/MathCoder-L-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MathLLMs/MathCoder-L-13B")
model = AutoModelForCausalLM.from_pretrained("MathLLMs/MathCoder-L-13B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MathLLMs/MathCoder-L-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MathLLMs/MathCoder-L-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MathLLMs/MathCoder-L-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MathLLMs/MathCoder-L-13B

SGLang

How to use MathLLMs/MathCoder-L-13B 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 "MathLLMs/MathCoder-L-13B" \
    --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": "MathLLMs/MathCoder-L-13B",
		"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 "MathLLMs/MathCoder-L-13B" \
        --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": "MathLLMs/MathCoder-L-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MathLLMs/MathCoder-L-13B with Docker Model Runner:
```
docker model run hf.co/MathLLMs/MathCoder-L-13B
```

MathCoder-L-13B / README.md

MathLLM

Update README.md

da10ecf verified about 2 years ago

preview code

raw

history blame

2.23 kB

	---
	license: mit
	language:
	- en
	metrics:
	- accuracy
	pipeline_tag: text-generation
	---
	# MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

	Paper: [https://arxiv.org/pdf/2310.03731.pdf](https://arxiv.org/pdf/2310.03731.pdf)

	Repo: [https://github.com/mathllm/MathCoder](https://github.com/mathllm/MathCoder)


	## Introduction
	We introduce MathCoder, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving.

	\| Base Model: Llama-2 \| Base Model: Code Llama \|
	\|-------------------------------------------------------------------\|-----------------------------------------------------------------------\|
	\| [MathCoder-L-7B](https://huggingface.co/MathLLM/MathCoder-L-7B) \| [MathCoder-CL-7B](https://huggingface.co/MathLLM/MathCoder-CL-7B) \|
	\| [MathCoder-L-13B](https://huggingface.co/MathLLM/MathCoder-L-13B) \| [MathCoder-CL-34B](https://huggingface.co/MathLLM/MathCoder-CL-34B) \|


	## Training Data
	The models are trained on the [MathCodeInstruct](https://huggingface.co/datasets/MathLLM/MathCodeInstruct) Dataset.


	## Training Procedure
	The models are fine-tuned with the MathCodeInstruct dataset using the original Llama-2 and CodeLlama models as base models. Check out our paper and repo for more details.

	## Evaluation

	<br>
	<div align="center">
	<img src="result.png" width="100%" title="Result Figure">
	</div>



	## Usage
	You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
	Check our Github repo for datails.


	## Citation
	Please cite the paper if you use our data, model or code.

	```
	@misc{wang2023mathcoder,
	title={MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning},
	author={Ke Wang and Houxing Ren and Aojun Zhou and Zimu Lu and Sichun Luo and Weikang Shi and Renrui Zhang and Linqi Song and Mingjie Zhan and Hongsheng Li},
	year={2023},
	eprint={2310.03731},
	archivePrefix={arXiv},
	primaryClass={cs.CL}
	}
	```