Instructions to use RaduGabriel/SirUkrainian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RaduGabriel/SirUkrainian with Transformers:

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

pipe = pipeline("text-generation", model="RaduGabriel/SirUkrainian")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RaduGabriel/SirUkrainian")
model = AutoModelForCausalLM.from_pretrained("RaduGabriel/SirUkrainian")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RaduGabriel/SirUkrainian with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RaduGabriel/SirUkrainian

SGLang

How to use RaduGabriel/SirUkrainian 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 "RaduGabriel/SirUkrainian" \
    --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": "RaduGabriel/SirUkrainian",
		"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 "RaduGabriel/SirUkrainian" \
        --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": "RaduGabriel/SirUkrainian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

NeuralPipe-7B-slerp

NeuralPipe-7B-slerp is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: RaduGabriel/MUZD
    parameters:
      weight: 0.3
  - model: RaduGabriel/Mistral-Instruct-Ukrainian-SFT
    parameters:
      weight: 0.3
  - model: Radu1999/MisterUkrainianDPO
    parameters:
      weight: 0.1
  - model: CultriX/NeuralTrix-7B-dpo
    parameters:
      weight: 0.3

merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "RaduGabriel/SirUkrainian"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.50
AI2 Reasoning Challenge (25-Shot)	67.32
HellaSwag (10-Shot)	85.54
MMLU (5-Shot)	63.14
TruthfulQA (0-shot)	68.74
Winogrande (5-shot)	81.53
GSM8k (5-shot)	56.71

Downloads last month: 103

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for RaduGabriel/SirUkrainian

CultriX/NeuralTrix-7B-dpo

Radu1999/MisterUkrainianDPO

RaduGabriel/MUZD

RaduGabriel/Mistral-Instruct-Ukrainian-SFT

Merge model

this model

Quantizations

1 model

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

67.320
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

85.540
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

63.140
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

68.740
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

81.530
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

56.710