philosophy-oracle-smollm2-360m/README.md

language, license, base_model, tags, pipeline_tag

language	license	base_model	tags	pipeline_tag
en	apache-2.0	HuggingFaceTB/SmolLM2-360M-Instruct	philosophy fine-tuned qlora smollm2 literature text-generation llama conversational	text-generation

Philosophy Oracle — SmolLM2 360M

A fine-tuned version of SmolLM2-360M-Instruct, trained on 2,000+ synthetic Q&A pairs derived from 34 philosophy and literature classics. The goal was simple: make a tiny model that thinks and speaks like the authors I love.

Model Details

Property	Value
Base Model	HuggingFaceTB/SmolLM2-360M-Instruct
Fine-tuning Method	QLoRA (4-bit)
Training Epochs	3
Training Pairs	~2,000
Merged Size	694 MB
GGUF (Q8_0) Size	386 MB
Framework	Unsloth Studio

Training Corpus

34 books across philosophy, existentialism, psychoanalysis, and literature. Pair counts weighted by philosophical depth:

Book	Pairs
Thus Spoke Zarathustra	150
Notes from Underground	120
The Myth of Sisyphus	121
Civilization and Its Discontents	100
The Possessed	100
Upanishads	112
The Fall	70
Totem and Taboo	70
The Interpretation of Dreams	70
Moby-Dick	70
The Symposium	80
Rig Veda	80
Book of Chuang Tzu	80
Tao Te Ching	100
Gilgamesh	70
The Social Contract	60
The Three Theban Plays	50
The Trial	50
The Death of Ivan Ilyich	50
The Oresteia	50
The Need for Roots	50
Four Archetypes	50
A Room of One's Own	40
Oppression and Liberty	40
Fathers and Sons	40
The Metamorphosis	40
War and Peace	40
The Bell Jar	30
To the Lighthouse	30
Wuthering Heights	30
The Picture of Dorian Gray	30
One Day in the Life of Ivan Denisovich	30
I Who Have Never Known Men	30
The Joke	30

Intended Use

• Philosophical Q&A with opinionated, crisp responses
• Edge deployment via Ollama or LM Studio using the GGUF
• Exploring what personality-driven fine-tuning looks like at 360M parameters

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "amitbehura/philosophy-oracle-smollm2-360m"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

messages = [
    {"role": "user", "content": "How should one live in the face of the certainty of death?"}
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt")
output = model.generate(input_ids, max_new_tokens=200)
print(tokenizer.decode(output[0]))

GGUF (Local Use)

Use philosophy-oracle-smollm2-360m-Q8_0.gguf with Ollama or LM Studio directly.

Limitations

• 360M parameter model — reasoning depth is limited by size
• Occasionally invents philosophical terminology to maintain persona
• Not suitable for factual Q&A — designed for philosophical voice, not accuracy
• Responses may reflect translator style rather than original author intent

Sample Output

Q: How should one live in the face of the certainty of death?

You have no choice but to live according to the circumstances that you have chosen. The certainty of death is not the problem; the problem is the life you live in the face of it. Each life is an experiment, and the experiment was chosen in part by the circumstances of death. Live according to the circumstances of your experiment, and then live.

Author

Built by Amit Behura as a personal experiment in personality-driven fine-tuning on a single laptop GPU (RTX 2050, 4GB VRAM).

Full writeup on the methodology, training decisions, and results available on Substack.