Instructions to use SeaLLMs/SeaLLM-7B-v2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SeaLLMs/SeaLLM-7B-v2.5 with Transformers:

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

pipe = pipeline("text-generation", model="SeaLLMs/SeaLLM-7B-v2.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SeaLLMs/SeaLLM-7B-v2.5")
model = AutoModelForCausalLM.from_pretrained("SeaLLMs/SeaLLM-7B-v2.5")
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

vLLM

How to use SeaLLMs/SeaLLM-7B-v2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SeaLLMs/SeaLLM-7B-v2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SeaLLMs/SeaLLM-7B-v2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SeaLLMs/SeaLLM-7B-v2.5

SGLang

How to use SeaLLMs/SeaLLM-7B-v2.5 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 "SeaLLMs/SeaLLM-7B-v2.5" \
    --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": "SeaLLMs/SeaLLM-7B-v2.5",
		"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 "SeaLLMs/SeaLLM-7B-v2.5" \
        --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": "SeaLLMs/SeaLLM-7B-v2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SeaLLMs/SeaLLM-7B-v2.5 with Docker Model Runner:
```
docker model run hf.co/SeaLLMs/SeaLLM-7B-v2.5
```

built on gemma or llama?

by YaoLiu61 - opened Apr 19, 2024

Discussion

YaoLiu61

Apr 19, 2024

Hi, this work is great! I benefits a lot from it. I have some questions.

In the Technical report, it says:
SeaLLMs are built upon the Llama-2 model and further advanced through continued pretraining, specialized instruction and alignment tuning.

But in the Model Card, it says:
SeaLLM-7B-v2.5 was built on top of Gemma-7b, and underwent large scale SFT and carefully designed alignment.

My questions are:

Was v2.5 built on Gemma or Llama ? when did it change from llama to gemma and why ?
If v2.5 was built on Gemma, it there a continue pretraining stage ?

Thanks a lot !

nxphi47

SeaLLMs - Language Models for Southeast Asian Languages org Apr 20, 2024

@YaoLiu61
The technical report was written for v1 and it was llama-2 based. seallm-7b-v2 is based on mistral-7b, and v2.5 is based on gemma-7b. The reason is we rely on strong English performance of other base model to build stronger performances in SEA languages. So we continuously update and improve SeaLLM models not only through better SEA-training-pipeline but also through the strongest English-focused models.

v2.5 is also continued pre-trained from gemma. Sorry for the confusion.

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