Instructions to use Shome/croguana-RC2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shome/croguana-RC2 with Transformers:

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

pipe = pipeline("text-generation", model="Shome/croguana-RC2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Shome/croguana-RC2")
model = AutoModelForCausalLM.from_pretrained("Shome/croguana-RC2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Shome/croguana-RC2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Shome/croguana-RC2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shome/croguana-RC2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Shome/croguana-RC2

SGLang

How to use Shome/croguana-RC2 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 "Shome/croguana-RC2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shome/croguana-RC2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Shome/croguana-RC2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shome/croguana-RC2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use Shome/croguana-RC2 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 Shome/croguana-RC2 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 Shome/croguana-RC2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Shome/croguana-RC2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Shome/croguana-RC2",
    max_seq_length=2048,
)

Docker Model Runner
How to use Shome/croguana-RC2 with Docker Model Runner:
```
docker model run hf.co/Shome/croguana-RC2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

⚠️ VAŽNA OBAVIJEST / IMPORTANT NOTICE

OGRANIČENJE ODGOVORNOSTI (DISCLAIMER) ZA KORISNIKE U RH

Ovaj model (CroGuana) je eksperimentalni istraživački projekt i NIJE namijenjen za produkcijsku upotrebu. Korištenjem modela prihvaćate sljedeće uvjete:

Istraživačka namjena: Model je razvijen isključivo u svrhe testiranja obrade hrvatskog jezika (NLP). Zabranjena je uporaba u komercijalne svrhe bez dodatnih sigurnosnih provjera.

Zabrana kritične primjene: Izričito je ZABRANJENO korištenje modela u sustavima koji mogu ugroziti život, zdravlje ili imovinu (npr. medicina, pravo, upravljanje strojevima, automatizirano donošenje odluka).

Nepredvidljivost: Model može generirati netočne, pristrane ili opasne informacije (hallucinations). Autor ne jamči za točnost izlaza.

Isključenje odgovornosti: Sukladno prijedlozima Zakona o provedbi Uredbe o AI u RH, autor (Tomislav Kraljević Shome) se u potpunosti odriče bilo kakve građanske ili kaznene odgovornosti za štetu (uključujući uništenje imovine) nastalu korištenjem ovog modela protivno navedenim uputama.

Odgovornost korisnika: Korisnik koji model "stavlja u pogon" ili integrira u druge sustave preuzima punu odgovornost za usklađenost s Aktom o AI i lokalnim zakonima.

Uploaded model

Developed by: Shome
License: cc-by-sa-4.0
Finetuned from model : gordicaleksa/YugoGPT

Model prompt:

"### Korisnik:\n[upit]\n### AI asistent:\n[odgovor]\n"

Fine tuning je za chat mode, gornji template se može produžiti koliko je potrebno.

Ctx size u trainu je 8192

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 49

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Shome/croguana-RC2

Base model

gordicaleksa/YugoGPT

Finetuned

(1)

this model

Quantizations

1 model

Shome
/

croguana-RC2

⚠️ VAŽNA OBAVIJEST / IMPORTANT NOTICE

Uploaded model

Model tree for Shome/croguana-RC2

Datasets used to train Shome/croguana-RC2