Instructions to use deloskiyt/gai-1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deloskiyt/gai-1.1 with LiteRT:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use deloskiyt/gai-1.1 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 deloskiyt/gai-1.1:F16
# Run inference directly in the terminal:
llama cli -hf deloskiyt/gai-1.1:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf deloskiyt/gai-1.1:F16
# Run inference directly in the terminal:
llama cli -hf deloskiyt/gai-1.1: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 deloskiyt/gai-1.1:F16
# Run inference directly in the terminal:
./llama-cli -hf deloskiyt/gai-1.1: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 deloskiyt/gai-1.1:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deloskiyt/gai-1.1:F16

Use Docker

docker model run hf.co/deloskiyt/gai-1.1:F16

LM Studio
Jan

vLLM

How to use deloskiyt/gai-1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deloskiyt/gai-1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deloskiyt/gai-1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deloskiyt/gai-1.1:F16

Ollama
How to use deloskiyt/gai-1.1 with Ollama:
```
ollama run hf.co/deloskiyt/gai-1.1:F16
```
Unsloth Desktop
Docker Model Runner
How to use deloskiyt/gai-1.1 with Docker Model Runner:
```
docker model run hf.co/deloskiyt/gai-1.1:F16
```

Lemonade

How to use deloskiyt/gai-1.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deloskiyt/gai-1.1:F16

Run and chat with the model

lemonade run user.gai-1.1-F16

List all available models

lemonade list

Atomic Chat

gai-1.1

Model generatywnej sztucznej inteligencji gai-1.1 (wersja z poprawkami stabilności, obsługą okna 2048 oraz wsparciem dla urządzeń mobilnych).

Parametry: ~7.5M parametrów (dokładnie: 7 488 384)
Wersja: 1.1
Okno kontekstowe: 2048 tokenów
Język: Polski (pl)

📁 Dostępne formaty w repozytorium:

🖥️ gai-1.1-F16.gguf — format GGUF dla LM Studio, llama.cpp i Ollama (z wbudowanym oknem 2048 i dedykowanym szablonem czatu)
📱 gai-1.1-iphone.litertlm — oficjalny format Google LiteRT-LM (.litertlm) dedykowany na iPhone (iOS) i urządzenia mobilne
📱 gai-1.1-iphone.litert — format LiteRT (.litert)
📦 gai-1.1-iphone.tflite — format TensorFlow Lite dla urządzeń mobilnych
🐍 model.safetensors — format PyTorch / Hugging Face Transformers

📜 Historia wersji

Pełną historię zmian i porównanie z wersją 1.0 znajdziesz w pliku VERSIONS.md.

Downloads last month: 17

Safetensors

Model size

7.49M params

Tensor type

F32