language, license_name, license_link, tags, base_model, pipeline_tag

language	license_name	license_link	tags	base_model	pipeline_tag
uk en	lfm1.0	https://www.liquid.ai/lfm-license	translation grpo ukrainian lfm2	Yehor/kulyk-uk-en	text-generation

kulyk-uk-en-grpo

Ukrainian-to-English translation model based on Yehor/kulyk-uk-en (LFM2-350M), improved with GRPO using calibrated guardrail rewards on WikiMatrix data.

Results

FLoRes+ devtest (sentence-by-sentence, greedy, repetition_penalty=1.05)

Model	BLEU	chrF	CometKiwi
kulyk-uk-en (baseline)	36.25	62.54	0.7401
kulyk-uk-en-grpo	37.03	63.25	0.7436

WMT24 uk-en (news domain, out-of-distribution)

Model	BLEU	chrF	CometKiwi
kulyk-uk-en (baseline)	27.90	54.49	0.6571
kulyk-uk-en-grpo	28.25	54.54	0.6598

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("iamthewalrus67/kulyk-uk-en-grpo", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("iamthewalrus67/kulyk-uk-en-grpo", trust_remote_code=True)

prompt = "Translate the text to English:\nПогода сьогодні чудова."
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True, return_tensors="pt", tokenize=True
).to(model.device)

output = model.generate(input_ids, max_new_tokens=256, do_sample=False, repetition_penalty=1.05)
print(tokenizer.decode(output[0][input_ids.shape[1]:], skip_special_tokens=True))

Training Details

• Method: GRPO with calibrated guardrail rewards
• Data: WikiMatrix uk-en (132K pairs)
• Rewards: chrF (0.30) + BLEU (0.25) + CometKiwi (0.20) + 5x calibrated guardrails (0.05 each)
• Training: Full fine-tune (no LoRA), single GPU, 300 steps
• Best checkpoint: step 100

See reward-driven-translation for full reproduction code.