Instructions to use Prithwiraj731/Granite-3.1-2b-FourWheeler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Prithwiraj731/Granite-3.1-2b-FourWheeler with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Prithwiraj731/Granite-3.1-2b-FourWheeler",
	filename="granite-2b-fp16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Prithwiraj731/Granite-3.1-2b-FourWheeler with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Prithwiraj731/Granite-3.1-2b-FourWheeler: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 Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Prithwiraj731/Granite-3.1-2b-FourWheeler: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 Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M

Use Docker

docker model run hf.co/Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M

LM Studio
Jan

vLLM

How to use Prithwiraj731/Granite-3.1-2b-FourWheeler with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Prithwiraj731/Granite-3.1-2b-FourWheeler"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Prithwiraj731/Granite-3.1-2b-FourWheeler",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M

Ollama
How to use Prithwiraj731/Granite-3.1-2b-FourWheeler with Ollama:
```
ollama run hf.co/Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M
```

Unsloth Studio

How to use Prithwiraj731/Granite-3.1-2b-FourWheeler 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 Prithwiraj731/Granite-3.1-2b-FourWheeler 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 Prithwiraj731/Granite-3.1-2b-FourWheeler to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Prithwiraj731/Granite-3.1-2b-FourWheeler to start chatting

How to use Prithwiraj731/Granite-3.1-2b-FourWheeler with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Prithwiraj731/Granite-3.1-2b-FourWheeler: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": "Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Prithwiraj731/Granite-3.1-2b-FourWheeler with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Prithwiraj731/Granite-3.1-2b-FourWheeler: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 Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Prithwiraj731/Granite-3.1-2b-FourWheeler with Docker Model Runner:
```
docker model run hf.co/Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M
```

Lemonade

How to use Prithwiraj731/Granite-3.1-2b-FourWheeler with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Prithwiraj731/Granite-3.1-2b-FourWheeler:Q4_K_M

Run and chat with the model

lemonade run user.Granite-3.1-2b-FourWheeler-Q4_K_M

List all available models

lemonade list

🚗 Granite-3.1-2b-FourWheeler

This model is a fine-tuned version of IBM Granite 3.1 2B Instruct, trained on a custom Four Wheeler dataset.

It has been trained using Unsloth for faster and memory-efficient fine-tuning.

📂 Included Files

Filename	Type	Description
`model.safetensors`	Safetensors	The full unquantized model weights (for Python/Transformers).
`granite-2b-q4_k_m.gguf`	GGUF (Q4)	Recommended. 4-bit quantized version. Fast & low memory (approx 1.5GB).
`granite-2b-fp16.gguf`	GGUF (FP16)	High-precision quantized version. Larger size (approx 4.8GB).

💻 How to Use (GGUF / Llama.cpp)

You can use the .gguf files with LM Studio, Ollama, or llama.cpp.

CLI Command:

./llama-cli -m granite-2b-q4_k_m.gguf -p "User: Which is the best 4-wheeler for off-roading?\nAssistant:" -cnv

🐍 How to Use (Python / Transformers)

To use the full model in Python:
Python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Prithwiraj731/Granite-3.1-2b-FourWheeler"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

prompt = "User: Tell me about the engine specifications of a seden car.\nAssistant:"

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=200)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

🔧 Training Details

    Base Model: ibm-granite/granite-3.1-2b-instruct

    Framework: Unsloth (PyTorch)

    Quantization: Q4_K_M & FP16 GGUF

    Fine-tuning type: LoRA (Low-Rank Adaptation)

Finetuned with ❤️ using Unsloth.

Downloads last month: 9

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Prithwiraj731/Granite-3.1-2b-FourWheeler

Base model

ibm-granite/granite-3.1-2b-base

Finetuned

ibm-granite/granite-3.1-2b-instruct

Quantized

(29)

this model

Quantizations

2 models