Instructions to use calcuis/openmath2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use calcuis/openmath2 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf calcuis/openmath2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf calcuis/openmath2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf calcuis/openmath2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf calcuis/openmath2: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 calcuis/openmath2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf calcuis/openmath2: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 calcuis/openmath2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf calcuis/openmath2:Q4_K_M

Use Docker

docker model run hf.co/calcuis/openmath2:Q4_K_M

LM Studio
Jan

vLLM

How to use calcuis/openmath2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "calcuis/openmath2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "calcuis/openmath2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/calcuis/openmath2:Q4_K_M

Ollama
How to use calcuis/openmath2 with Ollama:
```
ollama run hf.co/calcuis/openmath2:Q4_K_M
```
Unsloth Desktop

How to use calcuis/openmath2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf calcuis/openmath2:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "calcuis/openmath2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use calcuis/openmath2 with Docker Model Runner:
```
docker model run hf.co/calcuis/openmath2:Q4_K_M
```

Lemonade

How to use calcuis/openmath2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull calcuis/openmath2:Q4_K_M

Run and chat with the model

lemonade run user.openmath2-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use calcuis/openmath2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf calcuis/openmath2:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default calcuis/openmath2:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use calcuis/openmath2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf calcuis/openmath2:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "calcuis/openmath2:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

openmath2 / README.md

calcuis

Update README.md

51b3161 verified almost 2 years ago

preview code

Raw History Blame Contribute Delete

1.87 kB

	---
	license: llama3.1
	language:
	- en
	base_model:
	- nvidia/OpenMath2-Llama3.1-8B
	pipeline_tag: text-generation
	tags:
	- math
	- nvidia
	- llama
	---

	## GGUF quantized version of OpenMath2-Llama3.1-8B

	project original [source](https://huggingface.co/nvidia/OpenMath2-Llama3.1-8B) (finetuned model)

	Q_2_K (not nice)

	Q_3_K_S (acceptable)

	Q_3_K_M is acceptable (good for running with CPU)

	Q_3_K_L (acceptable)

	Q_4_K_S (okay)

	Q_4_K_M is recommanded (balance)

	Q_5_K_S (good)

	Q_5_K_M (good in general)

	Q_6_K is good also; if you want a better result; take this one instead of Q_5_K_M

	Q_8_0 which is very good; need a reasonable size of RAM otherwise you might expect a long wait

	f16 is similar to the original hf model; opt this one or hf also fine; make sure you have a good machine

	*the latest update includes Q_4_0, Q_4_1 (belong to Q4 family) and Q_5_0, Q_5_1 (Q5 family)

	### how to run it

	use any connector for interacting with gguf; i.e., [gguf-connector](https://pypi.org/project/gguf-connector/)

	<style>
	.image-container {
	display: flex;
	justify-content: center;
	align-items: center;
	gap: 20px;
	}
	.image-container img {
	width: 350px;
	height: auto;
	}
	</style>

	<div class="image-container">
	<img src="https://huggingface.co/nvidia/OpenMath2-Llama3.1-8B/resolve/main/scaling_plot.jpg" title="Performance of Llama-3.1-8B-Instruct as it is trained on increasing proportions of OpenMathInstruct-2">
	<img src="https://huggingface.co/nvidia/OpenMath2-Llama3.1-8B/resolve/main/math_level_comp.jpg" title="Comparison of OpenMath2-Llama3.1-8B vs. Llama-3.1-8B-Instruct across MATH levels">
	</div>

	the chart and figure above are from finetuned model (nvidia side); those are used for comparing between the finetuned model and the base model; and the base model is from meta