> ## Documentation Index
> Fetch the complete documentation index at: https://docs.liquid.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Bidirectional English to Korean translation CLI

<Card title="View Source Code" icon="github" href="https://github.com/Liquid4All/cookbook/tree/main/examples/lfm2-english-to-korean">
  Browse the complete example on GitHub
</Card>

## What's inside?

An efficient bidirectional translation system powered by Liquid AI's LFM2 1.2B model fine-tuned for Korean-English translation. This project demonstrates how domain-specific fine-tuning can achieve superior performance compared to models 3x larger, outperforming Google's Gemma-3 4B and Alibaba's Qwen3 4B on the Flores-200 benchmark.

Key features:

* **Automatic language detection** - Intelligently detects input language and translates accordingly
* **High-quality translation** - CHrF++ 32.96 / BLEU 12.05 on Flores-200 benchmark
* **Efficient inference** - Runs on modest hardware with merged adapters for speed
* **Easy-to-use CLI** - Simple command-line interface powered by Fire

*This project was built and released by [Kiwoong Yeom](https://www.linkedin.com/in/kiwoong-yeom/) with the support of [Maxime Labonne](https://www.linkedin.com/in/maxime-labonne/).*
*[Link to the original announcement on LinkedIn](https://www.linkedin.com/posts/activity-7406831565210583040-2B9p?utm_source=share\&utm_medium=member_desktop\&rcm=ACoAAAqH-bMBMXBij-GI7SN8H4dk_E4j4k19f_w)*

## Quick Start

1. Clone the repository

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
git clone https://github.com/Liquid4All/cookbook.git
cd cookbook/examples/lfm2-english-to-korean
```

2. Install dependencies

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
uv sync
```

3. Run translation example

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
uv run python main.py --text "$(cat linkedin_post.txt)" --max-new-tokens 1024
```

## Understanding the Architecture

The system uses a two-stage training approach:

1. **Supervised Fine-tuning (SFT)**: 100K high-quality Korean-English parallel datasets establish the translation foundation
2. **Reinforcement Learning (RL)**: GRPO optimization with 10K additional samples refines translation quality

### Model Components

* **Base Model**: `gyung/lfm2-1.2b-koen-mt-v4-100k` - SFT fine-tuned LFM2 1.2B
* **Adapter**: `gyung/lfm2-1.2b-koen-mt-v5-rl-10k-adapter` - LoRA adapter trained with GRPO
* **Automatic Detection**: Regular expression pattern matching for Korean text (Hangul syllables, Jamo)

The system automatically detects the input language and applies the appropriate translation direction, supporting both English→Korean and Korean→English translation.

## CLI Usage

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
uv run python main.py [OPTIONS]

Options:
  --text TEXT                    Text to translate (required)
  --model-name TEXT             Base model name (default: gyung/lfm2-1.2b-koen-mt-v4-100k)
  --adapter-name TEXT           Adapter name (default: gyung/lfm2-1.2b-koen-mt-v5-rl-10k-adapter)
  --max-new-tokens INTEGER     Maximum tokens to generate (default: 256)
  --temperature FLOAT          Sampling temperature (default: 0.3)
  --min-p FLOAT               Minimum probability threshold (default: 0.15)
  --repetition-penalty FLOAT   Repetition penalty (default: 1.05)
```

### Example Usage

Translate English to Korean:

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
uv run python main.py --text "Hello, how are you today?"
```

Translate Korean to English:

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
uv run python main.py --text "안녕하세요, 오늘 어떻게 지내세요?"
```

Process a file:

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
uv run python main.py --text "$(cat your_file.txt)" --max-new-tokens 1024
```

## Performance Benchmarks

On Flores-200 benchmark (1,012 samples):

| Model               | Parameters | CHrF++    | BLEU      |
| ------------------- | ---------- | --------- | --------- |
| **LFM2-KoEn-v5-RL** | **1.2B**   | **32.96** | **12.05** |
| Gemma-3-4B          | 4B         | 32.83     | 11.36     |
| Qwen3-4B            | 4B         | 25.62     | 7.46      |

The 1.2B parameter model outperforms models 3x larger, demonstrating that specialized training matters more than raw parameter count.

## Further Improvements

Next steps for enhanced performance and efficiency:

* **Speed optimization** with quantization techniques (GGUF, AWQ, GPTQ)
* **llama.cpp integration** for faster CPU inference
* **Full parameter RL training** with expanded compute resources
* **Length normalization removal** based on recent Qwen team findings
* **Extended dataset training** with 200K SFT + 25K RL samples

### Performance Optimization

The current implementation uses adapter merging for faster inference. Future improvements include:

* Quantized model variants for resource-constrained environments
* Streaming inference for real-time translation
* Batch processing for large document translation

## Need help?

<CardGroup cols={1}>
  <Card title="Join our Discord" icon="discord" iconType="brands" href="https://discord.gg/DFU3WQeaYD">
    Connect with the community and ask questions about this example.
  </Card>
</CardGroup>