Instructions to use Fu01978/OLMo-2-1B-openai-gsm8k-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Fu01978/OLMo-2-1B-openai-gsm8k-GGUF 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 Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Fu01978/OLMo-2-1B-openai-gsm8k-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 Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Fu01978/OLMo-2-1B-openai-gsm8k-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 Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Fu01978/OLMo-2-1B-openai-gsm8k-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fu01978/OLMo-2-1B-openai-gsm8k-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fu01978/OLMo-2-1B-openai-gsm8k-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M

Ollama
How to use Fu01978/OLMo-2-1B-openai-gsm8k-GGUF with Ollama:
```
ollama run hf.co/Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Fu01978/OLMo-2-1B-openai-gsm8k-GGUF with Docker Model Runner:
```
docker model run hf.co/Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M
```

Lemonade

How to use Fu01978/OLMo-2-1B-openai-gsm8k-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Fu01978/OLMo-2-1B-openai-gsm8k-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OLMo-2-1B-openai-gsm8k-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

OLMo-2-1B-openai-gsm8k-GGUF / README.md

Fu01978

Update README.md

11f894f verified 7 months ago

preview code

Raw

History Blame Contribute Delete

1.08 kB

	---
	license: apache-2.0
	language:
	- en
	base_model:
	- Fu01978/OLMo-2-1B-openai-gsm8k
	pipeline_tag: text-generation
	tags:
	- conversational
	- code
	- math
	- merge
	---

	# OLMo-2-1B-openai-gsm8k-GGUF

	This repository contains GGUF quantized versions of
	[Fu01978/OLMo-2-1B-openai-gsm8k](https://huggingface.co/Fu01978/OLMo-2-1B-openai-gsm8k),
	intended for efficient inference with llama.cpp-compatible runtimes.

	## What’s in this repo

	- GGUF quantized files for inference
	- No training code
	- No safetensors weights

	## What’s NOT in this repo

	- Original model
	- Training or fine-tuning scripts

	## Base Model

	These quantizations are derived from:

	Fu01978/OLMo-2-1B-openai-gsm8k
	👉 https://huggingface.co/Fu01978/OLMo-2-1B-openai-gsm8k

	Please refer to the base model card for:
	- Training data
	- Intended use
	- Limitations

	## Usage

	Example with llama.cpp:

	```bash
	./main \
	-m OLMo-2-1B-openai-gsm8k*.gguf \
	-p "Solve: 23 + 19 ="
	```

	## Notes on Quantization

	- Quantization may slightly reduce accuracy
	- Smaller sizes offer faster inference and lower VRAM usage