Instructions to use ByteDance-Seed/SAIL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance-Seed/SAIL-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ByteDance-Seed/SAIL-7B")

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

tokenizer = AutoTokenizer.from_pretrained("ByteDance-Seed/SAIL-7B")
model = AutoModelForCausalLM.from_pretrained("ByteDance-Seed/SAIL-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ByteDance-Seed/SAIL-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance-Seed/SAIL-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/SAIL-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ByteDance-Seed/SAIL-7B

SGLang

How to use ByteDance-Seed/SAIL-7B 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 "ByteDance-Seed/SAIL-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/SAIL-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ByteDance-Seed/SAIL-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/SAIL-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ByteDance-Seed/SAIL-7B with Docker Model Runner:
```
docker model run hf.co/ByteDance-Seed/SAIL-7B
```

SAIL-7B

Commit History

May 8, 2025

21:08
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
ae7a611

May 7, 2025

15:08
Upload pytorch_model.bin with huggingface_hub

leiwx52

Verified signature
45d917a
14:49
Upload tokenizer.model with huggingface_hub

leiwx52

Verified signature
f7ae5ef
14:49
Upload tokenizer_config.json with huggingface_hub

leiwx52

Verified signature
72853d1
14:48
Upload config.json with huggingface_hub

leiwx52

Verified signature
1acc165
14:48
Upload tokenizer.json with huggingface_hub

leiwx52

Verified signature
07ee540
14:47
Upload README.md with huggingface_hub

leiwx52

Verified signature
55a5d66
14:47
Upload generation_config.json with huggingface_hub

leiwx52

Verified signature
fae965c
14:47
Upload added_tokens.json with huggingface_hub

leiwx52

Verified signature
ff3f521
06:42
initial commit

leiwx52

Verified signature
a505433

Commit History

May 8, 2025

Adding `safetensors` variant of this model⁠

May 7, 2025

Upload pytorch_model.bin with huggingface_hub

Upload tokenizer.model with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload README.md with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload added_tokens.json with huggingface_hub

initial commit