Instructions to use aisingapore/Llama-SEA-LION-v3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aisingapore/Llama-SEA-LION-v3-8B with Transformers:

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

pipe = pipeline("text-generation", model="aisingapore/Llama-SEA-LION-v3-8B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aisingapore/Llama-SEA-LION-v3-8B")
model = AutoModelForCausalLM.from_pretrained("aisingapore/Llama-SEA-LION-v3-8B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aisingapore/Llama-SEA-LION-v3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aisingapore/Llama-SEA-LION-v3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aisingapore/Llama-SEA-LION-v3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aisingapore/Llama-SEA-LION-v3-8B

SGLang

How to use aisingapore/Llama-SEA-LION-v3-8B 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 "aisingapore/Llama-SEA-LION-v3-8B" \
    --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": "aisingapore/Llama-SEA-LION-v3-8B",
		"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 "aisingapore/Llama-SEA-LION-v3-8B" \
        --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": "aisingapore/Llama-SEA-LION-v3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aisingapore/Llama-SEA-LION-v3-8B with Docker Model Runner:
```
docker model run hf.co/aisingapore/Llama-SEA-LION-v3-8B
```

waiyiaisg commited on Apr 15, 2025

Commit

b5f04ba

verified ·

1 Parent(s): a51c9a8

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -23,7 +23,8 @@ base_model: meta-llama/Llama-3.1-8B-Instruct
 </div>
 # Llama-SEA-LION-v3-8B
-SEA-LION is a collection of Large Language Models (LLMs) which has been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
 Llama-SEA-LION-v3-8B is a multilingual model which has undergone continued pre-training on approximately **200B** tokens across 11 SEA languages: Burmese, Chinese, English, Filipino, Indonesia, Khmer, Lao, Malay, Tamil, Thai and Vietnamese.
@@ -45,7 +46,7 @@ For tokenisation, the model employs the default tokenizer used in Llama 3.1 8B I
 We evaluated Llama-SEA-LION-v3-8B on general language capabilities and constraint-following behaviour.
 #### General Language Capabilities and Constraint-following Behaviour
-For the evaluation of general language capabilities, we employed the [SEA-HELM (also known as BHASA) evaluation benchmark](https://arxiv.org/abs/2309.06085v2) across a variety of tasks.
 These tasks include Question Answering (QA), Sentiment Analysis (Sentiment), Toxicity Detection (Toxicity), Translation in both directions (Eng>Lang & Lang>Eng), Abstractive Summarisation (Abssum), Causal Reasoning (Causal) and Natural Language Inference (NLI).
 Note: SEA-HELM is implemented using prompts to elicit answers in a strict format. For all tasks, the model is expected to provide an answer tag from which the answer is automatically extracted. For tasks where options are provided, the answer should comprise one of the pre-defined options. The scores for each task is normalised to account for baseline performance due to random chance.

 </div>
 # Llama-SEA-LION-v3-8B
+[SEA-LION](https://arxiv.org/abs/2504.05747) is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
 Llama-SEA-LION-v3-8B is a multilingual model which has undergone continued pre-training on approximately **200B** tokens across 11 SEA languages: Burmese, Chinese, English, Filipino, Indonesia, Khmer, Lao, Malay, Tamil, Thai and Vietnamese.
 We evaluated Llama-SEA-LION-v3-8B on general language capabilities and constraint-following behaviour.
 #### General Language Capabilities and Constraint-following Behaviour
+For the evaluation of general language capabilities, we employed the [SEA-HELM evaluation benchmark](https://arxiv.org/abs/2502.14301) across a variety of tasks.
 These tasks include Question Answering (QA), Sentiment Analysis (Sentiment), Toxicity Detection (Toxicity), Translation in both directions (Eng>Lang & Lang>Eng), Abstractive Summarisation (Abssum), Causal Reasoning (Causal) and Natural Language Inference (NLI).
 Note: SEA-HELM is implemented using prompts to elicit answers in a strict format. For all tasks, the model is expected to provide an answer tag from which the answer is automatically extracted. For tasks where options are provided, the answer should comprise one of the pre-defined options. The scores for each task is normalised to account for baseline performance due to random chance.