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

Libraries

How to use Theoistic/gemma-3-1b-fo with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Theoistic/gemma-3-1b-fo", dtype="auto")

llama-cpp-python

How to use Theoistic/gemma-3-1b-fo with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Theoistic/gemma-3-1b-fo",
	filename="Theoistic-gemma-3-1b-fo-f16.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 Theoistic/gemma-3-1b-fo with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Theoistic/gemma-3-1b-fo:F16
# Run inference directly in the terminal:
llama-cli -hf Theoistic/gemma-3-1b-fo:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Theoistic/gemma-3-1b-fo:F16
# Run inference directly in the terminal:
llama-cli -hf Theoistic/gemma-3-1b-fo: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 Theoistic/gemma-3-1b-fo:F16
# Run inference directly in the terminal:
./llama-cli -hf Theoistic/gemma-3-1b-fo: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 Theoistic/gemma-3-1b-fo:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Theoistic/gemma-3-1b-fo:F16

Use Docker

docker model run hf.co/Theoistic/gemma-3-1b-fo:F16

LM Studio
Jan
Ollama
How to use Theoistic/gemma-3-1b-fo with Ollama:
```
ollama run hf.co/Theoistic/gemma-3-1b-fo:F16
```

Unsloth Studio

How to use Theoistic/gemma-3-1b-fo 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 Theoistic/gemma-3-1b-fo 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 Theoistic/gemma-3-1b-fo to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Theoistic/gemma-3-1b-fo to start chatting

Docker Model Runner
How to use Theoistic/gemma-3-1b-fo with Docker Model Runner:
```
docker model run hf.co/Theoistic/gemma-3-1b-fo:F16
```

Lemonade

How to use Theoistic/gemma-3-1b-fo with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Theoistic/gemma-3-1b-fo:F16

Run and chat with the model

lemonade run user.gemma-3-1b-fo-F16

List all available models

lemonade list

train_2025-11-21-18-29-32

This model is a fine-tuned version of google/gemma-3-1b-pt on the translation dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 2.0

Training results

Framework versions

Transformers 4.57.1
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.22.1

Downloads last month: 9

Safetensors

Model size

1.0B params

Tensor type

BF16

Inference Providers NEW

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

Model tree for Theoistic/gemma-3-1b-fo

Base model

google/gemma-3-1b-pt

Quantized

(21)

this model