Instructions to use leia-llm/Leia-Swallow-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leia-llm/Leia-Swallow-13b with Transformers:

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

pipe = pipeline("text-generation", model="leia-llm/Leia-Swallow-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("leia-llm/Leia-Swallow-13b")
model = AutoModelForCausalLM.from_pretrained("leia-llm/Leia-Swallow-13b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use leia-llm/Leia-Swallow-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leia-llm/Leia-Swallow-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leia-llm/Leia-Swallow-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/leia-llm/Leia-Swallow-13b

SGLang

How to use leia-llm/Leia-Swallow-13b 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 "leia-llm/Leia-Swallow-13b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leia-llm/Leia-Swallow-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "leia-llm/Leia-Swallow-13b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leia-llm/Leia-Swallow-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use leia-llm/Leia-Swallow-13b with Docker Model Runner:
```
docker model run hf.co/leia-llm/Leia-Swallow-13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Leia-Swallow-13B

LEIA is a training technique for autoregressive LLMs that effectively improves their performance in languages other than English by enhancing cross-lingual knowledge transfer from English to a target language. This model is constructed by applying LEIA to Swallow, a Japanese-English bilingual LLM based on LLaMA 2. The model achieves enhanced performance on four out of six Japanese question answering benchmarks and equivalent performance on the remaining two, as reported below.

Please refer to our paper or blog post (in Japanese) for further technical details.

Model List

Empirical Results

The model is assessed using the following six question answering benchmarks:

X-CODAH
X-CSQA
JCommonsenseQA
NIILC
JEMHopQA
JAQKET v2

Model	X-CODAH	X-CSQA	JCommonsenseQA	NIILC	JEMHopQA	JAQKET v2
Swallow	43.3	41.8	89.3	64.1	50.6	88.9
LEIA	44.0	41.9	89.3	65.8	50.6	89.6

For further details of this experiment, please refer to our paper.

Contributors

Ikuya Yamada (Studio Ousia, RIKEN)
Ryokan Ri (LY Corporation, SB Intuitions)

Downloads last month: 10

Safetensors

Model size

13B params

Tensor type

F32

Model tree for leia-llm/Leia-Swallow-13b

Quantizations

3 models

Paper for leia-llm/Leia-Swallow-13b

LEIA: Facilitating Cross-Lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation

Paper • 2402.11485 • Published Feb 18, 2024 • 1