Instructions to use arthurmello/gemma-3-1b-it-paul-graham with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arthurmello/gemma-3-1b-it-paul-graham with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="arthurmello/gemma-3-1b-it-paul-graham")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arthurmello/gemma-3-1b-it-paul-graham")
model = AutoModelForCausalLM.from_pretrained("arthurmello/gemma-3-1b-it-paul-graham", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use arthurmello/gemma-3-1b-it-paul-graham with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arthurmello/gemma-3-1b-it-paul-graham with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arthurmello/gemma-3-1b-it-paul-graham"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arthurmello/gemma-3-1b-it-paul-graham",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arthurmello/gemma-3-1b-it-paul-graham

SGLang

How to use arthurmello/gemma-3-1b-it-paul-graham with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "arthurmello/gemma-3-1b-it-paul-graham" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arthurmello/gemma-3-1b-it-paul-graham",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "arthurmello/gemma-3-1b-it-paul-graham" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arthurmello/gemma-3-1b-it-paul-graham",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arthurmello/gemma-3-1b-it-paul-graham with Docker Model Runner:
```
docker model run hf.co/arthurmello/gemma-3-1b-it-paul-graham
```

Model Card for `gemma-3b-it-paul-graham-lora`

This is a fine-tuned version of the google/gemma-3b-it model using LoRA (Low-Rank Adaptation), trained to generate essays in the style of Paul Graham.

Model Details

Model Description

This model adapts google/gemma-3b-it using LoRA fine-tuning on a collection of Paul Graham's essays. It is intended for creative writing and stylistic emulation of Paul Graham’s tone and argumentative structure.

Developed by: Arthur Mello
Model type: Causal Language Model (Decoder-only)
Language(s) (NLP): English
Finetuned from model: google/gemma-3b-it

Uses

Direct Use

The model can be used to generate essays or long-form answers in the style of Paul Graham. It is useful for educational, literary, or entertainment purposes.

Out-of-Scope Use

Factual question answering (it may hallucinate)
Use in high-risk domains (e.g., legal, medical)
Emulating real individuals without clear consent

Bias, Risks, and Limitations

The model inherits biases from the original Gemma model and the Paul Graham dataset. Since the dataset reflects a single author's perspective, generated outputs may lean toward specific ideological or philosophical stances.

Recommendations

Users should review outputs carefully and avoid using the model as a source of truth or factual information.

How to Get Started with the Model

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("arthurmello/gemma-3b-it-paul-graham-lora")
tokenizer = AutoTokenizer.from_pretrained("arthurmello/gemma-3b-it-paul-graham-lora")

prompt = "<start_of_turn>user\nWrite an essay on the future of AI<end_of_turn><eos>\n<start_of_turn>model\n"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=300)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

Training Data

The model was fine-tuned on a cleaned dataset of Paul Graham’s essays, formatted into a chat-like structure using a custom chat_template.

Dataset: arthurmello/paul-graham-essays

Training Procedure

Training Hyperparameters

LoRA rank: 16
LoRA alpha: 64
LoRA dropout: 0.05
Batch size: 1 (gradient accumulation = 4)
Max sequence length: 1500 tokens
Learning rate: 1e-4
Precision: bf16
Epochs: 10
Scheduler: cosine
Weight decay: 0.1

Evaluation

Metrics

Training loss: Decreased from 2.57 to 1.80
Validation loss: Plateaued around 2.5–2.6, indicating stability with limited overfitting

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator.

Hardware Type: L4 GPU
Hours used: ~30 min
Cloud Provider: Google Colab Pro
Compute Region: Europe

Technical Specifications

Model Architecture and Objective

Decoder-only transformer model with LoRA adapters applied to key projection layers, attention outputs, and feedforward projections.

Compute Infrastructure

Hardware

1× NVIDIA L4 (22.5GB)

Software

Python 3.11
PyTorch
Hugging Face Transformers, PEFT, TRL

Model Card Contact

For questions or feedback, contact @arthurmello or LinkedIn

Downloads last month: 6

Safetensors

Model size

1B params

Tensor type

F32

BF16

Model tree for arthurmello/gemma-3-1b-it-paul-graham

Base model

google/gemma-3-27b-pt

Finetuned

google/gemma-3-27b-it

Adapter

(247)

this model

Dataset used to train arthurmello/gemma-3-1b-it-paul-graham

Paper for arthurmello/gemma-3-1b-it-paul-graham

LoRA: Low-Rank Adaptation of Large Language Models

Paper • 2106.09685 • Published Jun 17, 2021 • 64

Model Card for gemma-3b-it-paul-graham-lora