Instructions to use kurakurai/Luth-0.6B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kurakurai/Luth-0.6B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="kurakurai/Luth-0.6B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kurakurai/Luth-0.6B-Instruct")
model = AutoModelForCausalLM.from_pretrained("kurakurai/Luth-0.6B-Instruct", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kurakurai/Luth-0.6B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kurakurai/Luth-0.6B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kurakurai/Luth-0.6B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kurakurai/Luth-0.6B-Instruct

SGLang

How to use kurakurai/Luth-0.6B-Instruct 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 "kurakurai/Luth-0.6B-Instruct" \
    --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": "kurakurai/Luth-0.6B-Instruct",
		"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 "kurakurai/Luth-0.6B-Instruct" \
        --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": "kurakurai/Luth-0.6B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kurakurai/Luth-0.6B-Instruct with Docker Model Runner:
```
docker model run hf.co/kurakurai/Luth-0.6B-Instruct
```

Luth-0.6B-Instruct / README.md

MaxLSB

Update README.md

a1f901d verified about 1 year ago

preview code

Raw

History Blame

1.43 kB

	---
	library_name: transformers
	license: apache-2.0
	datasets:
	- kurakurai/luth-sft
	language:
	- fr
	- en
	base_model:
	- Qwen/Qwen3-0.6B
	pipeline_tag: text-generation
	---

	![Kurakura AI Logo](media/logo_kurakura.png)

	# Luth-0.6B

	Luth-0.6B is a French fine-tuned version of [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B), trained on the [Luth-SFT](https://huggingface.co/datasets/kurakurai/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.

	## Model Details

	Luth-0.6B was trained using full fine-tuning on the Luth-SFT dataset with [Axolotl](https://github.com/axolotl-ai-cloud/axolotl). The resulting model was then merged with the base Qwen3-0.6B model. This process successfully retained the model's English capabilities while improving its performance on nearly all benchmarks in both French and English.

	## Benchmark Results

	French Evaluation:

	![French Evaluation](media/french_evaluation.png)

	English Evaluation:

	![English Evaluation](media/english_evaluation.png)

	## Citation

	```bibtex
	@misc{luth2025kurakurai,
	title = {Luth-0.6B},
	author = {Kurakura AI Team},
	year = {2025},
	howpublished = {\url{https://huggingface.co/kurakurai/Luth-0.6B}},
	note = {Qwen3-0.6B fine-tuned on French datasets}
	}
	```