Luth-1.7B-Instruct

Luth-1.7B-Instruct is a French fine-tuned version of Qwen3-1.7B, trained on the Luth-SFT dataset. The model has drastically improved its French capabilities in instruction following, math, and general knowledge. Additionally, its English capabilities have remained stable and have even increased in some areas.

Our Evaluation, training and data scripts are available on GitHub, along with the Blog we wrote.

Model Details

Luth was trained using full fine-tuning on the Luth-SFT dataset with Axolotl. The resulting model was then merged with the base Qwen3-1.7B model. This process successfully retained the model's English capabilities while improving its performance on most selected benchmarks in both French and English.

Benchmark Results

We used LightEval for evaluation, with custom tasks for the French benchmarks. The models were evaluated with a temperature=0.

French Benchmark Scores

Model	IFEval French	GPQA-Diamond French	MMLU French	Math500 French	Arc-Challenge French	Hellaswag French
Luth-1.7B-Instruct	58.53	36.55	49.75	62.60	35.16	31.88
Qwen3-1.7B	54.71	31.98	28.49	60.40	33.28	24.86
SmolLM2-1.7B-Instruct	30.93	20.30	33.73	10.20	28.57	49.58
Qwen2.5-1.5B-Instruct	31.30	27.41	46.25	33.20	32.68	34.33
LFM2-1.2B	54.41	22.84	47.59	36.80	39.44	33.05

English Benchmark Scores

Model	IFEval English	GPQA-Diamond English	MMLU English	Math500 English	Arc-Challenge English	Hellaswag English
Luth-1.7B-Instruct	65.80	29.80	60.28	70.40	42.24	58.53
Qwen3-1.7B	68.88	31.82	52.82	71.20	36.18	46.98
SmolLM2-1.7B-Instruct	49.04	25.08	50.27	22.67	42.32	66.94
Qwen2.5-1.5B-Instruct	39.99	25.76	59.81	57.20	41.04	64.48
LFM2-1.2B	68.52	24.24	55.22	45.80	42.58	57.61

Code Example

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kurakurai/Luth-1.7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("kurakurai/Luth-1.7B-Instruct")
messages = [
    {"role": "user", "content": "Quelle est la capitale de la France?"},
]
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=100)
print(
    tokenizer.decode(
        outputs[0][inputs["input_ids"].shape[-1] :], skip_special_tokens=True
    )
)

Citation

@misc{luth2025kurakurai,
  title   = {Luth-1.7B-Instruct},
  author  = {Maxence Lasbordes, Sinoué Gad},
  year    = {2025},
  howpublished = {\url{https://huggingface.co/kurakurai/Luth-1.7B-Instruct}},
}