> ## 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.
# LFM2-350M-ENJP-MT
> 350M parameter model for bidirectional English-Japanese translation
← Back to Liquid Nanos
LFM2-350M-ENJP-MT is a specialized translation model for near real-time bidirectional Japanese/English translation. Optimized for short-to-medium text with low latency.
## Specifications
| Property | Value |
| -------------- | ------------------- |
| Parameters | 350M |
| Context Length | 32K tokens |
| Task | Machine Translation |
| Languages | English ↔ Japanese |
Low-latency inference
EN→JP and JP→EN
Compact model size
## Prompting Recipe
This model requires a specific system prompt to specify translation direction. Single-turn conversations only.
**System Prompts:**
* `"Translate to Japanese."` — English → Japanese
* `"Translate to English."` — Japanese → English
## Quick Start
**Install:**
```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
pip install "transformers>=5.2.0" torch accelerate
```
**English to Japanese:**
```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "LiquidAI/LFM2-350M-ENJP-MT"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
messages = [
{"role": "system", "content": "Translate to Japanese."},
{"role": "user", "content": "What is C. elegans?"}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
# Output: C. elegansとは何ですか？
```
**Japanese to English:**
```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
messages = [
{"role": "system", "content": "Translate to English."},
{"role": "user", "content": "今日は天気がいいですね。"}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
# Output: The weather is nice today.
```
**Download GGUF:**
```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
hf download LiquidAI/LFM2-350M-ENJP-MT-GGUF \
--local-dir ./LFM2-350M-ENJP-MT-GGUF
```
**Run:**
```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
# English to Japanese
llama-cli -m ./LFM2-350M-ENJP-MT-GGUF/LFM2-350M-ENJP-MT-Q4_K_M.gguf \
-sys "Translate to Japanese." \
-p "Hello, how are you?"
# Japanese to English
llama-cli -m ./LFM2-350M-ENJP-MT-GGUF/LFM2-350M-ENJP-MT-Q4_K_M.gguf \
-sys "Translate to English." \
-p "こんにちは、元気ですか？"
```