Instructions to use theprint/PyRe-3B-v2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theprint/PyRe-3B-v2-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("theprint/PyRe-3B-v2-GGUF", dtype="auto")

llama-cpp-python

How to use theprint/PyRe-3B-v2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="theprint/PyRe-3B-v2-GGUF",
	filename="unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use theprint/PyRe-3B-v2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theprint/PyRe-3B-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf theprint/PyRe-3B-v2-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 theprint/PyRe-3B-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf theprint/PyRe-3B-v2-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 theprint/PyRe-3B-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf theprint/PyRe-3B-v2-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 theprint/PyRe-3B-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theprint/PyRe-3B-v2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/theprint/PyRe-3B-v2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use theprint/PyRe-3B-v2-GGUF with Ollama:
```
ollama run hf.co/theprint/PyRe-3B-v2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use theprint/PyRe-3B-v2-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 theprint/PyRe-3B-v2-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 theprint/PyRe-3B-v2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theprint/PyRe-3B-v2-GGUF to start chatting

Pi new

How to use theprint/PyRe-3B-v2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf theprint/PyRe-3B-v2-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "PyRe-3B-v2-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use theprint/PyRe-3B-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/theprint/PyRe-3B-v2-GGUF:Q4_K_M
```

Lemonade

How to use theprint/PyRe-3B-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theprint/PyRe-3B-v2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.PyRe-3B-v2-GGUF-Q4_K_M

List all available models

lemonade list

PyRe is Experimental

Please note that this model is a WIP experiment into GRPO fine tuning on Python code problems for reasoning. The performance of this model varies greatly depending on task, prompt and parameters.

I recommend a very low temperature, like 0.1. You may also see more consistent results by encouraging the use of <think> and <answer> tags in the system prompt.

Example System Prompt

Think through complex problems carefully, before giving the user your final answer. Use <think> and </think> to encapsulate your thoughts.

This GGUF is based on theprint/PyRe-3B-v2.

Uploaded model

Developed by: theprint
License: apache-2.0
Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 19

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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