Instructions to use Skywork/Skywork-13B-Base-3.1TB with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Skywork/Skywork-13B-Base-3.1TB with Transformers:

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

pipe = pipeline("text-generation", model="Skywork/Skywork-13B-Base-3.1TB", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Skywork/Skywork-13B-Base-3.1TB", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Skywork/Skywork-13B-Base-3.1TB with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Skywork/Skywork-13B-Base-3.1TB"
# 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-13B-Base-3.1TB",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Skywork/Skywork-13B-Base-3.1TB

SGLang

How to use Skywork/Skywork-13B-Base-3.1TB 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-13B-Base-3.1TB" \
    --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-13B-Base-3.1TB",
		"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-13B-Base-3.1TB" \
        --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-13B-Base-3.1TB",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Skywork/Skywork-13B-Base-3.1TB with Docker Model Runner:
```
docker model run hf.co/Skywork/Skywork-13B-Base-3.1TB
```

error "ModuleNotFoundError: No module named 'transformers_modules.Skywork.Skywork-13B-Base-3'"

by breadlicker45 - opened Nov 1, 2023

Discussion

breadlicker45

Nov 1, 2023

how do i fix this?

weitianwen

Skywork org Nov 1, 2023

Did you try other versions of Skywork-13B?

breadlicker45

Nov 1, 2023

•

edited Nov 1, 2023

Did you try other versions of Skywork-13B?

13b math worked (that's the only other one I tested)

zhao1iang

Nov 2, 2023

It appears that Hugging Face splits the model name based on dots. You can download the 3.1TB model parameters, rename the model to 3TB, and then use the model dictionary as input.

idekoh

Nov 3, 2023

How do I exactly download the model parameters? sorry I'm new to this field

weitianwen

Skywork org Nov 3, 2023

How do I exactly download the model parameters? sorry I'm new to this field

There is a tab "Files and versions", where you can click to download model parameter files, e.g. pytorch_model-00001-of-00053.bin

weitianwen changed discussion status to closed Nov 3, 2023

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