Instructions to use Skywork/Skywork-MoE-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Skywork/Skywork-MoE-Base with Transformers:

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

pipe = pipeline("text-generation", model="Skywork/Skywork-MoE-Base", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Skywork/Skywork-MoE-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Skywork/Skywork-MoE-Base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Skywork/Skywork-MoE-Base

SGLang

How to use Skywork/Skywork-MoE-Base 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 "Skywork/Skywork-MoE-Base" \
    --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": "Skywork/Skywork-MoE-Base",
		"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 "Skywork/Skywork-MoE-Base" \
        --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": "Skywork/Skywork-MoE-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Skywork/Skywork-MoE-Base with Docker Model Runner:
```
docker model run hf.co/Skywork/Skywork-MoE-Base
```

Skywork-MoE-Base

Commit History

Jan 9, 2025

14:10
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
91a6394

Jul 31, 2024

06:49
Update configuration_skywork_moe.py

zhao1iang

Verified signature
ede88fd
06:48
Update config.json

zhao1iang

Verified signature
6f38345

Jun 12, 2024

09:25
Update README.md

zhao1iang

Verified signature
452b672

Jun 3, 2024

09:28
Update README.md

BBuf

Verified signature
9b598e0
09:26
Update README.md

BBuf

Verified signature
752bcef
09:25
Update README.md

BBuf

Verified signature
47bdd71
09:17
Update README.md

BBuf

Verified signature
84f68dc
09:00
Update README.md

BBuf

Verified signature
531028a
08:42
Update README.md

BBuf

Verified signature
7174d94
08:40
Update README.md

BBuf

Verified signature
a5bf20b
08:36
Update README.md

BBuf

Verified signature
f7f2fef
02:46
Upload skywork_moe_base_evaluation.png

zhao1iang

Verified signature
1b0321f
02:46
Upload skywork_moe_base_evaluation.png

zhao1iang

Verified signature
771abb9
02:25
Upload 5 files

zhao1iang

Verified signature
d5f5665
02:07
Update README.md

zhao1iang

Verified signature
565ab8c

May 31, 2024

17:25
update model and config

liang.zhao

5019740
12:06
initial commit

zhao1iang

Verified signature
92427c8

Commit History

Jan 9, 2025

Adding `safetensors` variant of this model⁠

Jul 31, 2024

Update configuration_skywork_moe.py

Update config.json

Jun 12, 2024

Update README.md

Jun 3, 2024

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Upload skywork_moe_base_evaluation.png

Upload skywork_moe_base_evaluation.png

Upload 5 files

Update README.md

May 31, 2024

update model and config

initial commit