Instructions to use alkibijad/YugoGPT-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alkibijad/YugoGPT-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("alkibijad/YugoGPT-GGUF", dtype="auto")

llama-cpp-python

How to use alkibijad/YugoGPT-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="alkibijad/YugoGPT-GGUF",
	filename="YugoGPT.Q4_1.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use alkibijad/YugoGPT-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf alkibijad/YugoGPT-GGUF:Q4_1
# Run inference directly in the terminal:
llama-cli -hf alkibijad/YugoGPT-GGUF:Q4_1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf alkibijad/YugoGPT-GGUF:Q4_1
# Run inference directly in the terminal:
llama-cli -hf alkibijad/YugoGPT-GGUF:Q4_1

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 alkibijad/YugoGPT-GGUF:Q4_1
# Run inference directly in the terminal:
./llama-cli -hf alkibijad/YugoGPT-GGUF:Q4_1

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 alkibijad/YugoGPT-GGUF:Q4_1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alkibijad/YugoGPT-GGUF:Q4_1

Use Docker

docker model run hf.co/alkibijad/YugoGPT-GGUF:Q4_1

LM Studio
Jan
Ollama
How to use alkibijad/YugoGPT-GGUF with Ollama:
```
ollama run hf.co/alkibijad/YugoGPT-GGUF:Q4_1
```

Unsloth Studio

How to use alkibijad/YugoGPT-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 alkibijad/YugoGPT-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 alkibijad/YugoGPT-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use alkibijad/YugoGPT-GGUF with Docker Model Runner:
```
docker model run hf.co/alkibijad/YugoGPT-GGUF:Q4_1
```

Lemonade

How to use alkibijad/YugoGPT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alkibijad/YugoGPT-GGUF:Q4_1

Run and chat with the model

lemonade run user.YugoGPT-GGUF-Q4_1

List all available models

lemonade list

O modelu

YugoGPT je trenutno najbolji "open source" model za srpski, hrvatski, bosanski... i sve ostale jezike na koje uspemo da se "podelimo" 🙂

Ovaj repozitorijum sadrži model u GGUF formatu, koji je pogodan za korišćenje modela u lokalu i ne zahteva skupe grafičke kartice.

Verzije modela

Da bi model radio brže, kompresovan je u nekoliko manjih verzija. Kompresijom se neznatno gubi na kvalitetu, ali se znatno dobija na brzini.

Preporučeno je koristiti Q4_1 verziju jer je najbrža.

Naziv	Veličina (GB)	Napomena
Q4_1	4.55	Težine su kompresovane na 4 bita. Najbrža verzija.
q8_0	7.7	Težine su kompresovane na 8 bita.
fp16	14.5	Težine se čuvaju kao 16 bita.
fp32	29	Originalne, 32 bitne težine. Nepotrebno za korišćenje na lokalnom računaru

Kako koristiti ovaj model na svom računaru?

LMStudio - najlakši način ⚡️

Najlakši način je da se prvo instalira LMStudio, program koji omogućuva veoma lako korišćenje LLM-ova.

Nakon instalacije, u polju za pretragu ukucaj "alkibijad/YugoGPT":
Izaberi neki od modela (preporučeno Q4_1):
Nakon što se model "skine", klikni na "chat" u levom delu ekrana i možeš da ćaskaš sa modelom.
[Opciono] Možeš da podesiš "system prompt", npr. "Ti si AI asistent koji uvek želi da pomogne." ili kako god već hoćeš.

To je to!

llama.cpp - napredno 🤓

Ako si napredan korisnik i želiš da se petljaš sa komandnom linijom i naučiš više o GGUF formatu, idi na llama.cpp i pročitaj uputstva 🙂

Naredni koraci 🐾

Ovaj repozitorijum je plod mini projekta za upoznavanje sa GGUF formatom. Ovo bi mogli biti naredni koraci, ali teško da će do njih doći:

[] Konvertovanje u još neke od varijanti (npr. 5 bitova, 2 bita itd.) Ovo teško da ću raditi pošto je zapravo to već uradjeno ovde 🙌
[] Kačenje koda za konverziju. U suštini dovoljno je pratiti ova uputstva.

Downloads last month: 118

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

16-bit

32-bit

Inference Providers NEW

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

Model tree for alkibijad/YugoGPT-GGUF

Base model

gordicaleksa/YugoGPT

Quantized

(11)

this model