Instructions to use harshalmore31/naval_gemma-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use harshalmore31/naval_gemma-3 with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("harshalmore31/naval_gemma-3", dtype="auto")

llama-cpp-python

How to use harshalmore31/naval_gemma-3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="harshalmore31/naval_gemma-3",
	filename="gemma-3-finetune.Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use harshalmore31/naval_gemma-3 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 harshalmore31/naval_gemma-3:Q8_0
# Run inference directly in the terminal:
llama cli -hf harshalmore31/naval_gemma-3:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf harshalmore31/naval_gemma-3:Q8_0
# Run inference directly in the terminal:
llama cli -hf harshalmore31/naval_gemma-3:Q8_0

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 harshalmore31/naval_gemma-3:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf harshalmore31/naval_gemma-3:Q8_0

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 harshalmore31/naval_gemma-3:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf harshalmore31/naval_gemma-3:Q8_0

Use Docker

docker model run hf.co/harshalmore31/naval_gemma-3:Q8_0

LM Studio
Jan
Ollama
How to use harshalmore31/naval_gemma-3 with Ollama:
```
ollama run hf.co/harshalmore31/naval_gemma-3:Q8_0
```

Unsloth Studio

How to use harshalmore31/naval_gemma-3 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 harshalmore31/naval_gemma-3 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 harshalmore31/naval_gemma-3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for harshalmore31/naval_gemma-3 to start chatting

Atomic Chat new
Docker Model Runner
How to use harshalmore31/naval_gemma-3 with Docker Model Runner:
```
docker model run hf.co/harshalmore31/naval_gemma-3:Q8_0
```

Lemonade

How to use harshalmore31/naval_gemma-3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull harshalmore31/naval_gemma-3:Q8_0

Run and chat with the model

lemonade run user.naval_gemma-3-Q8_0

List all available models

lemonade list

naval-gemma: AI Model Emulating Naval Ravikant's Wisdom

Model Overview

naval-gemma is an AI language model fine-tuned to emulate the wisdom and insights of Naval Ravikant, a renowned entrepreneur and philosopher. Built upon Google DeepMind's Gemma-3-4B architecture, this model offers responses reflecting Naval's perspectives on topics like wealth, happiness, and decision-making.

Model Details

Model Architecture: Gemma-3-4B
Fine-Tuning Dataset: Extracted from "The Almanack of Naval Ravikant" by Eric Jorgenson
Quantization: GGUF Q8_0 (4.1GB)
Inference Platforms: Compatible with Ollama and llama.cpp for local, offline usage

Usage

To utilize naval-gemma locally:

Pull the Model:
```
ollama pull harshalmore31/naval-gemma
```
Run the Model:
```
ollama run harshalmore31/naval-gemma
```

Note: Ensure Ollama or llama.cpp is installed and configured on your system.

Example Interaction

Prompt: "How can I build wealth without luck?"

Response: "Play long-term games with long-term people. Build specific knowledge, apply leverage, and let compounding work over time."

License

This model is fine-tuned on public content from "The Almanack of Naval Ravikant" and distributed for educational and research purposes. Commercial use or redistribution should comply with fair use and original content ownership rights.

Acknowledgements

Naval Ravikant: For his timeless wisdom
Eric Jorgenson: Author of "The Almanack of Naval Ravikant"
Google DeepMind: Developers of the Gemma-3-4B model
Ollama & llama.cpp: Tools enabling local AI inference

Contact

For inquiries or contributions, please reach out via GitHub or Hugging Face.

Uploaded finetuned model

Developed by: harshalmore31
License: apache-2.0
Finetuned from model : unsloth/gemma-3-4b-it-unsloth-bnb-4bit

This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 2

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for harshalmore31/naval_gemma-3

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

unsloth/gemma-3-4b-it-unsloth-bnb-4bit