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

Libraries

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

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

pipe = pipeline("text-generation", model="SeaLLMs/SeaLLM-7B-v2.5-mlx-quantized")
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("SeaLLMs/SeaLLM-7B-v2.5-mlx-quantized")
model = AutoModelForCausalLM.from_pretrained("SeaLLMs/SeaLLM-7B-v2.5-mlx-quantized", 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 SeaLLMs/SeaLLM-7B-v2.5-mlx-quantized 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-mlx-quantized"
# 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-mlx-quantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

SeaLLM-7B-v2.5 - Large Language Models for Southeast Asia

Technical Blog 🤗 Tech Memo 🤗 DEMO Github Technical Report

We introduce SeaLLM-7B-v2.5, the state-of-the-art multilingual LLM for Southeast Asian (SEA) languages 🇬🇧 🇨🇳 🇻🇳 🇮🇩 🇹🇭 🇲🇾 🇰🇭 🇱🇦 🇲🇲 🇵🇭. It is the most significant upgrade since SeaLLM-13B, with half the size, outperforming performance across diverse multilingual tasks, from world knowledge, math reasoning, instruction following, etc.

This is Q4 quantized version for MLX for apple silicon. Checkout SeaLLM-7B-v2.5 page for more details.

Citation

If you find our project useful, we hope you would kindly star our repo and cite our work as follows: Corresponding Author: l.bing@alibaba-inc.com

Author list and order will change!

* and ^ are equal contributions.

@article{damonlpsg2023seallm,
  author = {Xuan-Phi Nguyen*, Wenxuan Zhang*, Xin Li*, Mahani Aljunied*, Weiwen Xu, Hou Pong Chan,
            Zhiqiang Hu, Chenhui Shen^, Yew Ken Chia^, Xingxuan Li, Jianyu Wang,
            Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang,
            Chaoqun Liu, Hang Zhang, Lidong Bing},
  title = {SeaLLMs - Large Language Models for Southeast Asia},
  year = 2023,
  Eprint = {arXiv:2312.00738},
}

Downloads last month: 14

Safetensors

Model size

2B params

Tensor type

F16

U32

Collection including SeaLLMs/SeaLLM-7B-v2.5-mlx-quantized

SeaLLM-7B-v2.5

Collection

SeaLLM-7B-v2.5 and its quantized variants. • 3 items • Updated Jul 11, 2024

Paper for SeaLLMs/SeaLLM-7B-v2.5-mlx-quantized

SeaLLMs -- Large Language Models for Southeast Asia

Paper • 2312.00738 • Published Dec 1, 2023 • 23