Instructions to use QuantFactory/MathCoder2-CodeLlama-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/MathCoder2-CodeLlama-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/MathCoder2-CodeLlama-7B-GGUF",
	filename="MathCoder2-CodeLlama-7B.Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/MathCoder2-CodeLlama-7B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/MathCoder2-CodeLlama-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/MathCoder2-CodeLlama-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/MathCoder2-CodeLlama-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M

Ollama
How to use QuantFactory/MathCoder2-CodeLlama-7B-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/MathCoder2-CodeLlama-7B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/MathCoder2-CodeLlama-7B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/MathCoder2-CodeLlama-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/MathCoder2-CodeLlama-7B-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/MathCoder2-CodeLlama-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/MathCoder2-CodeLlama-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/MathCoder2-CodeLlama-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MathCoder2-CodeLlama-7B-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/MathCoder2-CodeLlama-7B-GGUF

This is quantized version of MathGenie/MathCoder2-CodeLlama-7B created using llama.cpp

Original Model Card

MathCoder2

Introduction

The MathCoder2 models are created by conducting continued pretraining on MathCode-Pile. They are introduced in the paper MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code.

The mathematical pretraining dataset includes mathematical code accompanied with natural language reasoning steps, making it a superior resource for models aimed at performing advanced mathematical reasoning tasks.

Evaluation

Citation

If you find this repository helpful, please consider citing our papers:

@misc{lu2024mathcoder2bettermathreasoning,
      title={MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code}, 
      author={Zimu Lu and Aojun Zhou and Ke Wang and Houxing Ren and Weikang Shi and Junting Pan and Mingjie Zhan and Hongsheng Li},
      year={2024},
      eprint={2410.08196},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.08196}, 
}

@inproceedings{
wang2024mathcoder,
title={MathCoder: Seamless Code Integration in {LLM}s for Enhanced Mathematical Reasoning},
author={Zimu Lu and Aojun Zhou and Zimu Lu and Sichun Luo and Weikang Shi and Renrui Zhang and Linqi Song and Mingjie Zhan and Hongsheng Li},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=z8TW0ttBPp}
}

Downloads last month: 334

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for QuantFactory/MathCoder2-CodeLlama-7B-GGUF

Base model

codellama/CodeLlama-7b-hf

Quantized

(36)

this model

Dataset used to train QuantFactory/MathCoder2-CodeLlama-7B-GGUF

Paper for QuantFactory/MathCoder2-CodeLlama-7B-GGUF

MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code

Paper • 2410.08196 • Published Oct 10, 2024 • 48