Instructions to use aisingapore/Apertus-SEA-LION-v4-8B-IT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aisingapore/Apertus-SEA-LION-v4-8B-IT with Transformers:

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

pipe = pipeline("text-generation", model="aisingapore/Apertus-SEA-LION-v4-8B-IT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aisingapore/Apertus-SEA-LION-v4-8B-IT")
model = AutoModelForCausalLM.from_pretrained("aisingapore/Apertus-SEA-LION-v4-8B-IT", device_map="auto")
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 aisingapore/Apertus-SEA-LION-v4-8B-IT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aisingapore/Apertus-SEA-LION-v4-8B-IT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aisingapore/Apertus-SEA-LION-v4-8B-IT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aisingapore/Apertus-SEA-LION-v4-8B-IT

SGLang

How to use aisingapore/Apertus-SEA-LION-v4-8B-IT 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/Apertus-SEA-LION-v4-8B-IT" \
    --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": "aisingapore/Apertus-SEA-LION-v4-8B-IT",
		"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 "aisingapore/Apertus-SEA-LION-v4-8B-IT" \
        --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": "aisingapore/Apertus-SEA-LION-v4-8B-IT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aisingapore/Apertus-SEA-LION-v4-8B-IT with Docker Model Runner:
```
docker model run hf.co/aisingapore/Apertus-SEA-LION-v4-8B-IT
```

SAnocha commited on May 20

Commit

32a109a

verified ·

1 Parent(s): 3037fb3

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -1,18 +1,18 @@
 ---
 library_name: transformers
 base_model:
-  - swiss-ai/Apertus-8B-Instruct-2509
 language:
-  - en
-  - zh
-  - vi
-  - id
-  - th
-  - fil
-  - ta
-  - ms
-  - my
-license: apache-2.0
 base_model_relation: finetune
 pipeline_tag: text-generation
 ---
@@ -50,7 +50,7 @@ For tokenization, the model employs the default tokenizer used in Apertus-8B-Ins
 - **Model type:** Decoder
 - **Context length:** 65k
 - **Language(s):** Indonesian, Vietnamese, Thai, Filipino, Tamil, Burmese, Malay
-- **License:** [Apache-2.0](https://choosealicense.com/licenses/apache-2.0/)
 - **Finetuned from model:** [Apertus-8B-Instruct](https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509)
 ### Model Sources

 ---
 library_name: transformers
 base_model:
+- swiss-ai/Apertus-8B-Instruct-2509
 language:
+- en
+- zh
+- vi
+- id
+- th
+- fil
+- ta
+- ms
+- my
+license: mit
 base_model_relation: finetune
 pipeline_tag: text-generation
 ---
 - **Model type:** Decoder
 - **Context length:** 65k
 - **Language(s):** Indonesian, Vietnamese, Thai, Filipino, Tamil, Burmese, Malay
+- **License:** [MIT](https://mit-license.org/)
 - **Finetuned from model:** [Apertus-8B-Instruct](https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509)
 ### Model Sources