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:

  1. Pull the Model:

    ollama pull harshalmore31/naval-gemma
    
  2. 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
32
GGUF
Model size
3.88B params
Architecture
gemma3

8-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for harshalmore31/naval_gemma-3

Quantized
(8)
this model

Dataset used to train harshalmore31/naval_gemma-3