Instructions to use Fibogacci/Qra-1B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fibogacci/Qra-1B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Fibogacci/Qra-1B-GGUF",
	filename="qra-1b.Q8_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Fibogacci/Qra-1B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Fibogacci/Qra-1B-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Fibogacci/Qra-1B-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Fibogacci/Qra-1B-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Fibogacci/Qra-1B-GGUF:Q8_0

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 Fibogacci/Qra-1B-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Fibogacci/Qra-1B-GGUF:Q8_0

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 Fibogacci/Qra-1B-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Fibogacci/Qra-1B-GGUF:Q8_0

Use Docker

docker model run hf.co/Fibogacci/Qra-1B-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use Fibogacci/Qra-1B-GGUF with Ollama:
```
ollama run hf.co/Fibogacci/Qra-1B-GGUF:Q8_0
```

Unsloth Studio new

How to use Fibogacci/Qra-1B-GGUF 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 Fibogacci/Qra-1B-GGUF 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 Fibogacci/Qra-1B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Fibogacci/Qra-1B-GGUF to start chatting

Docker Model Runner
How to use Fibogacci/Qra-1B-GGUF with Docker Model Runner:
```
docker model run hf.co/Fibogacci/Qra-1B-GGUF:Q8_0
```

Lemonade

How to use Fibogacci/Qra-1B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Fibogacci/Qra-1B-GGUF:Q8_0

Run and chat with the model

lemonade run user.Qra-1B-GGUF-Q8_0

List all available models

lemonade list

Qra is a series of LLMs adapted to the Polish language, resulting from a collaboration between the National Information Processing Institute (OPI) and Gdańsk University of Technology (PG).

Original base model can be found on HuggingFace here: https://huggingface.co/OPI-PG/Qra-1b

This GGUF file was quantized using Colab Notebook: https://colab.research.google.com/github/adithya-s-k/LLM-Alchemy-Chamber/blob/main/Quantization/GGUF_Quantization.ipynb

This is my first convertion of model. I don't know if whole process was correct (I mean model/gguf file gives strange answers, maybe I'm configuring it or setting not properly), but I'm fresh learner.

Pierwsze boty za płoty, jak to mówią.

Gratuluję twórcom, miejmy nadzieję, że będzie to Qra znosząca złote jajka.

Pozdro!

Downloads last month: 15

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for Fibogacci/Qra-1B-GGUF

Base model

OPI-PG/Qra-1b

Quantized

(4)

this model