Instructions to use aisingapore/SEA-LION-v1-7B-IT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aisingapore/SEA-LION-v1-7B-IT with Transformers:

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

pipe = pipeline("text-generation", model="aisingapore/SEA-LION-v1-7B-IT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aisingapore/SEA-LION-v1-7B-IT", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("aisingapore/SEA-LION-v1-7B-IT", trust_remote_code=True, 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aisingapore/SEA-LION-v1-7B-IT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aisingapore/SEA-LION-v1-7B-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/SEA-LION-v1-7B-IT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aisingapore/SEA-LION-v1-7B-IT

SGLang

How to use aisingapore/SEA-LION-v1-7B-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/SEA-LION-v1-7B-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/SEA-LION-v1-7B-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/SEA-LION-v1-7B-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/SEA-LION-v1-7B-IT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aisingapore/SEA-LION-v1-7B-IT with Docker Model Runner:
```
docker model run hf.co/aisingapore/SEA-LION-v1-7B-IT
```

can't run the model using vllm

by agoudarzi - opened Apr 9, 2024

Discussion

agoudarzi

Apr 9, 2024

when I try this model with vllm I this error:

    return engine_class(*args, **kwargs)
  File "/home/codespace/vllm/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 110, in __init__
    self.model_executor = executor_class(model_config, cache_config,
  File "/home/codespace/vllm/lib/python3.10/site-packages/vllm/executor/gpu_executor.py", line 37, in __init__
    self._init_worker()
  File "/home/codespace/vllm/lib/python3.10/site-packages/vllm/executor/gpu_executor.py", line 66, in _init_worker
    self.driver_worker.load_model()
  File "/home/codespace/vllm/lib/python3.10/site-packages/vllm/worker/worker.py", line 107, in load_model
    self.model_runner.load_model()
  File "/home/codespace/vllm/lib/python3.10/site-packages/vllm/worker/model_runner.py", line 95, in load_model
    self.model = get_model(
  File "/home/codespace/vllm/lib/python3.10/site-packages/vllm/model_executor/model_loader.py", line 91, in get_model
    model = model_class(model_config.hf_config, linear_method)
  File "/home/codespace/vllm/lib/python3.10/site-packages/vllm/model_executor/models/mpt.py", line 257, in __init__
    self.transformer = MPTModel(config, linear_method)
  File "/home/codespace/vllm/lib/python3.10/site-packages/vllm/model_executor/models/mpt.py", line 208, in __init__
    assert config.embedding_fraction == 1.0
AssertionError

RaymondAISG

AI Singapore org Apr 11, 2024

Dear @agoudarzi ,

As SEA-LION architecture is not natively supported by vLLM, additional adaptation is required for SEA-LION to run on vLLM.
Kindly refer to the readme here for the instructions on running SEA-LION with vLLM.
https://github.com/aisingapore/sealion/tree/vllm/vllm

Hope this helps.
Raymond

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment