Instructions to use aisingapore/Gemma-SEA-LION-v3-9B-IT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aisingapore/Gemma-SEA-LION-v3-9B-IT with Transformers:

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

pipe = pipeline("text-generation", model="aisingapore/Gemma-SEA-LION-v3-9B-IT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("aisingapore/Gemma-SEA-LION-v3-9B-IT")
model = AutoModelForMultimodalLM.from_pretrained("aisingapore/Gemma-SEA-LION-v3-9B-IT")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aisingapore/Gemma-SEA-LION-v3-9B-IT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aisingapore/Gemma-SEA-LION-v3-9B-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/Gemma-SEA-LION-v3-9B-IT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aisingapore/Gemma-SEA-LION-v3-9B-IT

SGLang

How to use aisingapore/Gemma-SEA-LION-v3-9B-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/Gemma-SEA-LION-v3-9B-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/Gemma-SEA-LION-v3-9B-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/Gemma-SEA-LION-v3-9B-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/Gemma-SEA-LION-v3-9B-IT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aisingapore/Gemma-SEA-LION-v3-9B-IT with Docker Model Runner:
```
docker model run hf.co/aisingapore/Gemma-SEA-LION-v3-9B-IT
```

tainc commited on Oct 30, 2024

Commit

992f563

verified ·

1 Parent(s): 207e356

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -95,10 +95,10 @@ Current SEA-LION models, including this commercially permissive release, have no
 ## Technical Specifications
 ### Fine-Tuning Details
-Gemma2 9B CPT SEA-LIONv3 Instruct was built using a combination of a full parameter fine-tune, alignment, alongside model merges of the best performing checkpoints. The training process for fine-tuning was approximately 15 hours, with alignment taking 2 hours on 8x H100-80GB GPUs.
 ## Data
-Gemma2 9B CPT SEA-LIONv3 Instruct was trained on a wide range of synthetic instructions alongside those hand-curated by the team, with the assistance of native speakers. In addition, special care was taken to ensure that the datasets used had commercially permissive licenses through verification with the original data source.
 ## Call for Contributions
 We encourage researchers, developers, and language enthusiasts to actively contribute to the enhancement and expansion of SEA-LION. Contributions can involve identifying and reporting bugs, sharing pre-training, instruction, and preference data, improving documentation usability, proposing and implementing new model evaluation tasks and metrics, or training versions of the model in additional Southeast Asian languages. Join us in shaping the future of SEA-LION by sharing your expertise and insights to make these models more accessible, accurate, and versatile. Please check out our GitHub for further information on the call for contributions.

 ## Technical Specifications
 ### Fine-Tuning Details
+Gemma2 9B CPT SEA-LIONv3 Instruct was built using a combination of a full parameter fine-tune, on-policy alignment, and model merges of the best performing checkpoints. The training process for fine-tuning was approximately 15 hours, with alignment taking 2 hours, both on 8x H100-80GB GPUs.
 ## Data
+Gemma2 9B CPT SEA-LIONv3 Instruct was trained on a wide range of synthetic instructions, alongside publicly available instructions hand-curated by the team with the assistance of native speakers. In addition, special care was taken to ensure that the datasets used had commercially permissive licenses through verification with the original data source.
 ## Call for Contributions
 We encourage researchers, developers, and language enthusiasts to actively contribute to the enhancement and expansion of SEA-LION. Contributions can involve identifying and reporting bugs, sharing pre-training, instruction, and preference data, improving documentation usability, proposing and implementing new model evaluation tasks and metrics, or training versions of the model in additional Southeast Asian languages. Join us in shaping the future of SEA-LION by sharing your expertise and insights to make these models more accessible, accurate, and versatile. Please check out our GitHub for further information on the call for contributions.