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

Libraries

How to use Prithwiraj731/Granite-3.1-2b-TwoWheeler 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-TwoWheeler",
	filename="granite-3.1-2b-instruct.F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Prithwiraj731/Granite-3.1-2b-TwoWheeler 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-TwoWheeler:F16
# Run inference directly in the terminal:
llama-cli -hf Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16

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-TwoWheeler:F16
# Run inference directly in the terminal:
llama-cli -hf Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16

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-TwoWheeler:F16
# Run inference directly in the terminal:
./llama-cli -hf Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16

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-TwoWheeler:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16

Use Docker

docker model run hf.co/Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16

LM Studio
Jan

vLLM

How to use Prithwiraj731/Granite-3.1-2b-TwoWheeler 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-TwoWheeler"
# 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-TwoWheeler",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16

Ollama
How to use Prithwiraj731/Granite-3.1-2b-TwoWheeler with Ollama:
```
ollama run hf.co/Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16
```

Unsloth Studio new

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

Pi new

How to use Prithwiraj731/Granite-3.1-2b-TwoWheeler 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-TwoWheeler:F16

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-TwoWheeler:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Prithwiraj731/Granite-3.1-2b-TwoWheeler 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-TwoWheeler:F16

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-TwoWheeler:F16

Run Hermes

hermes

Docker Model Runner
How to use Prithwiraj731/Granite-3.1-2b-TwoWheeler with Docker Model Runner:
```
docker model run hf.co/Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Prithwiraj731/Granite-3.1-2b-TwoWheeler:F16

Run and chat with the model

lemonade run user.Granite-3.1-2b-TwoWheeler-F16

List all available models

lemonade list

🏍️ Granite-3.1-2b-TwoWheeler

This model is a fine-tuned version of IBM Granite 3.1 2B Instruct, specialized in Two-Wheeler knowledge (Motorcycles, Scooters, Superbikes, and Maintenance).

It was trained using Unsloth on a custom dataset to provide expert advice on bike specifications, comparisons, comparisons, and troubleshooting.

📂 Included Files

This repository contains the full merged model and quantized versions:

Filename	Type	Description
`model.safetensors`	Full Model	The unquantized, merged weights. Use this for Python/Transformers training or inference.
`granite-3.1-2b-instruct.Q4_K_M.gguf`	GGUF (Q4)	Recommended. 4-bit quantized. Fast & efficient (runs on 4GB+ RAM).
`granite-3.1-2b-instruct.F16.gguf`	GGUF (FP16)	High-precision uncompressed GGUF. Best quality but larger file size.

💻 How to Use (GGUF / Llama.cpp / LM Studio)

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

CLI Command (llama.cpp):

./llama-cli -m granite-3.1-2b-instruct.Q4_K_M.gguf -p "User: Which bike is best for daily city commute with high mileage in India?\nAssistant:" -cnv

System Prompt (Recommended):

    You are an expert automotive assistant specializing in two-wheelers. Provide detailed specifications, comparisons, and maintenance advice for bikes and scooters.

🐍 How to Use (Python / Transformers)

Since the model is merged, you can load it directly without needing LoRA adapters.
Python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

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

# Load Tokenizer & Model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=torch.float16 # Use bfloat16 if your GPU supports it
)

# Format the Prompt (Granite Chat Format)
messages = [
    {"role": "user", "content": "Compare the Royal Enfield Classic 350 vs Honda CB350. Which one has better vibrations?"}
]
input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Generate
inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)

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

🔧 Training Details

    Base Architecture: IBM Granite 3.1 (2 Billion Parameters)

    Framework: Unsloth (PyTorch)

    Quantization: Q4_K_M & FP16 GGUF

    Fine-tuning Method: Full LoRA Merge (16-bit)

    Dataset Focus: Technical specifications, riding comfort, mileage, and maintenance of two-wheelers.

Finetuned with ❤️ using Unsloth.

Downloads last month: 16

Safetensors

Model size

3B params

Tensor type

BF16

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

Base model

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

Finetuned

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

Quantized

(29)

this model

Quantizations

1 model