Instructions to use Yehor/kulyk-en-uk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yehor/kulyk-en-uk with Transformers:

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

pipe = pipeline("text-generation", model="Yehor/kulyk-en-uk")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yehor/kulyk-en-uk")
model = AutoModelForCausalLM.from_pretrained("Yehor/kulyk-en-uk")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use Yehor/kulyk-en-uk with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Yehor/kulyk-en-uk",
	filename="kulyk-en-uk-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Yehor/kulyk-en-uk with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Yehor/kulyk-en-uk:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Yehor/kulyk-en-uk:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Yehor/kulyk-en-uk:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Yehor/kulyk-en-uk: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 Yehor/kulyk-en-uk:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Yehor/kulyk-en-uk: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 Yehor/kulyk-en-uk:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Yehor/kulyk-en-uk:Q8_0

Use Docker

docker model run hf.co/Yehor/kulyk-en-uk:Q8_0

LM Studio
Jan

vLLM

How to use Yehor/kulyk-en-uk with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Yehor/kulyk-en-uk:Q8_0

SGLang

How to use Yehor/kulyk-en-uk 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 "Yehor/kulyk-en-uk" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yehor/kulyk-en-uk",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Yehor/kulyk-en-uk" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yehor/kulyk-en-uk",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Yehor/kulyk-en-uk with Ollama:
```
ollama run hf.co/Yehor/kulyk-en-uk:Q8_0
```

Unsloth Studio new

How to use Yehor/kulyk-en-uk 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 Yehor/kulyk-en-uk 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 Yehor/kulyk-en-uk to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Yehor/kulyk-en-uk to start chatting

Docker Model Runner
How to use Yehor/kulyk-en-uk with Docker Model Runner:
```
docker model run hf.co/Yehor/kulyk-en-uk:Q8_0
```

Lemonade

How to use Yehor/kulyk-en-uk with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Yehor/kulyk-en-uk:Q8_0

Run and chat with the model

lemonade run user.kulyk-en-uk-Q8_0

List all available models

lemonade list

A lightweight model to do machine translation from English to Ukrainian based on recently published LFM2 model. Use demo to test it.

Also, there's another model: kulyk-uk-en

Run with Docker (CPU):

docker run -p 3000:3000 --rm ghcr.io/egorsmkv/kulyk-rust:latest

Run using Apptainer (CUDA):

Run it using shell:

apptainer shell --nv ./kulyk.sif

Apptainer> /opt/entrypoints/kulyk --verbose --n-len 1024 --model-path-ue /project/models/kulyk-uk-en.gguf --model-path-eu /project/models/kulyk-en-uk.gguf

Run it as a webservice:

apptainer instance start --nv ./kulyk.sif kulyk-ws

# go to http://localhost:3000

Facts:

Fine-tuned with 40M samples (filtered by quality metric) from ~53.5M for 1.4 epochs
354M params
Requires 1 GB of RAM to run with bf16
BLEU on FLORES-200: 27.24
Tokens per second: 229.93 (bs=1), 1664.40 (bs=10), 8392.48 (bs=64)
License: lfm1.0

Info:

Model name is inherited from name of Sergiy Kulyk who was chargé d'affaires of Ukraine in the United States

Training Info:

Learning Rate: 3e-5
Learning Rate scheduler type: cosine
Warmup Ratio: 0.05
Max length: 2048
Batch Size: 10
packed=True
Sentences <= 1000 chars
Gradient accumulation steps: 4
Used Flash Attention 2
Time for epoch: 32 hours
2 cards of NVIDIA RTX 3090 Ti (24G)
accelerate with DeepSpeed, offloading into CPU
Memory usage: 22.212GB-22.458GB
torch 2.7.1

Acknowledgements:

Serhiy Stetskovych for providing compute to train this model
lang-uk members for their compilation of different MT datasets

Downloads last month: 63

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for Yehor/kulyk-en-uk

Base model

LiquidAI/LFM2-350M

Quantized

(33)

this model

Finetunes

1 model

Quantizations

3 models

Dataset used to train Yehor/kulyk-en-uk

Spaces using Yehor/kulyk-en-uk 3

Evaluation results

BLEU on FLORES
self-reported

27.240