Instructions to use mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B with Transformers:

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

pipe = pipeline("text-generation", model="mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B")
model = AutoModelForMultimodalLM.from_pretrained("mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B")
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 mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B

SGLang

How to use mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B 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 "mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B" \
    --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": "mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B",
		"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 "mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B" \
        --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": "mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B",
    max_seq_length=2048,
)

Docker Model Runner
How to use mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B with Docker Model Runner:
```
docker model run hf.co/mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Uploaded finetuned Llama-3.1-Swallow-JP-EN-Translator-v1-8B model

Prompt format: ChatML

Recommended system prompt: You are a helpful assistant that translates Japanese to English.

Recommended sampling settings: temperature 0.5 (or lower), repetition penalty 1.04 (or higher if needed)

LoRA: mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-LoRA-8B

Seems to perform better when translating from Japanese to English. Doing English to Japanese doesn't seem to really work.

Training used LoRA rank 128 and alpha set to 32. Context length was set to 16384. But the there's more data in 8k context length so using 8k context length will likely perform better.

Training data was this: mpasila/ParallelFiction-Ja_En-1k-16k-Gemma-3-ShareGPT-Filtered

Original dataset (before filtering/cleaning): NilanE/ParallelFiction-Ja_En-100k