Instructions to use nold/OpenMath-Mistral-7B-v0.1-hf-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nold/OpenMath-Mistral-7B-v0.1-hf-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nold/OpenMath-Mistral-7B-v0.1-hf-GGUF",
	filename="OpenMath-Mistral-7B-v0.1-hf_Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nold/OpenMath-Mistral-7B-v0.1-hf-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nold/OpenMath-Mistral-7B-v0.1-hf-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 nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nold/OpenMath-Mistral-7B-v0.1-hf-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 nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nold/OpenMath-Mistral-7B-v0.1-hf-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 nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M

Use Docker

docker model run hf.co/nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use nold/OpenMath-Mistral-7B-v0.1-hf-GGUF with Ollama:
```
ollama run hf.co/nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M
```

Unsloth Studio

How to use nold/OpenMath-Mistral-7B-v0.1-hf-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 nold/OpenMath-Mistral-7B-v0.1-hf-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 nold/OpenMath-Mistral-7B-v0.1-hf-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nold/OpenMath-Mistral-7B-v0.1-hf-GGUF to start chatting

Docker Model Runner
How to use nold/OpenMath-Mistral-7B-v0.1-hf-GGUF with Docker Model Runner:
```
docker model run hf.co/nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M
```

Lemonade

How to use nold/OpenMath-Mistral-7B-v0.1-hf-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nold/OpenMath-Mistral-7B-v0.1-hf-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OpenMath-Mistral-7B-v0.1-hf-GGUF-Q4_K_M

List all available models

lemonade list

OpenMath-Mistral-7B-v0.1-hf

OpenMath models were designed to solve mathematical problems by integrating text-based reasoning with code blocks executed by Python interpreter. The models were trained on OpenMathInstruct-1, a math instruction tuning dataset with 1.8M problem-solution pairs generated using permissively licensed Mixtral-8x7B model.

	greedy		majority@50
model	GSM8K	MATH	GMS8K	MATH
OpenMath-CodeLlama-7B (nemo \| HF)	75.9	43.6	84.8	55.6
OpenMath-Mistral-7B (nemo \| HF)	80.2	44.5	86.9	57.2
OpenMath-CodeLlama-13B (nemo \| HF)	78.8	45.5	86.8	57.6
OpenMath-CodeLlama-34B (nemo \| HF)	80.7	48.3	88.0	60.2
OpenMath-Llama2-70B (nemo \| HF)	84.7	46.3	90.1	58.3
OpenMath-CodeLlama-70B (nemo \| HF)	84.6	50.7	90.8	60.4

The pipeline we used to produce these models is fully open-sourced!

See our paper for more details!

How to use the models?

Try to run inference with our models with just a few commands!

Reproducing our results

We provide all instructions to fully reproduce our results.

Improving other models

To improve other models or to learn more about our code, read through the docs below.

NeMo-Skills Pipeline

In our pipeline we use NVIDIA NeMo, an end-to-end, cloud-native framework to build, customize, and deploy generative AI models anywhere. It includes training and inferencing frameworks, guardrailing toolkits, data curation tools, and pretrained models, offering enterprises an easy, cost-effective, and fast way to adopt generative AI.

Citation

If you find our work useful, please consider citing us!

@article{toshniwal2024openmath,
  title   = {OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset},
  author  = {Shubham Toshniwal and Ivan Moshkov and Sean Narenthiran and Daria Gitman and Fei Jia and Igor Gitman},
  year    = {2024},
  journal = {arXiv preprint arXiv: Arxiv-2402.10176}
}

Quantization of Model nvidia/OpenMath-Mistral-7B-v0.1-hf. Created using llm-quantizer Pipeline

Downloads last month: 21

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nold/OpenMath-Mistral-7B-v0.1-hf-GGUF

Base model

mistralai/Mistral-7B-v0.1

Quantized

(187)

this model

Dataset used to train nold/OpenMath-Mistral-7B-v0.1-hf-GGUF

Paper for nold/OpenMath-Mistral-7B-v0.1-hf-GGUF

OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

Paper • 2402.10176 • Published Feb 15, 2024 • 38