README.md

---
library_name: transformers
license: other
license_name: lfm1.0
license_link: LICENSE
language:
- en
- ja
pipeline_tag: translation
tags:
- liquid
- lfm2
- edge
- translation
- japanese
base_model:
- LiquidAI/LFM2-350M-ENJP-MT
---

<center>
<div style="text-align: center;">
  <img 
    src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" 
    alt="Liquid AI"
    style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;"
  />
</div>
<div style="display: flex; justify-content: center; gap: 0.5em;">
  <a href="https://playground.liquid.ai/chat">
<a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> • <a href="https://docs.liquid.ai/lfm"><strong>Documentation</strong></a> • <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a></a>
</div>
</center>

# LFM2-350M-ENJP-MT-GGUF

Based on the [LFM2-350M](https://huggingface.co/LiquidAI/LFM2-350M) model, this checkpoint has been fine-tuned for near real-time **bi-directional Japanese/English translation** of short-to-medium inputs.

Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2-350M-ENJP-MT

## 🏃 How to run LFM2

Example usage with [llama.cpp](https://github.com/ggml-org/llama.cpp):

Translating to English.
```
llama-cli -hf LiquidAI/LFM2-350M-ENJP-MT-GGUF -sys "Translate to English." -st
```

Translate to Japanese.
```
llama-cli -hf LiquidAI/LFM2-350M-ENJP-MT-GGUF -sys "Translate to Japanese." -st
```

Quantized model.
```
llama-cli -hf LiquidAI/LFM2-350M-ENJP-MT-GGUF:Q4_0 -sys "Translate to Japanese." -st
```