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
```

Intermediate Checkpoints

by puffy310 - opened Nov 20, 2023

Discussion

puffy310

Nov 20, 2023

I understand it may be cumbersome, but has the team considered releasing more intermediate checkpoints? IF you have them on hand or are training another one, consider releasing checkpoints in closer intervals similar to Pythia.

weitianwen

Skywork org Nov 20, 2023

Yes, it is entirely possible to release more intermediate checkpoints, e.g. 500B, 1T, 1.5T, 2T, 2.5T, 3T. Would that meet your needs?

puffy310

Nov 20, 2023

That would be great! My proposal is that there is a new repository called "Skywork-13B-Base-Intermediate" where every checkpoint saved as a different branch in one repo. https://huggingface.co/EleutherAI/pythia-70m That would be a great effort to make a good alternative to Pythia. If it's saved and not critical to anything Huggingface storage is free anyways so might as well put all you have. Just my opinion. Thank you for responding!

weitianwen

Skywork org Nov 21, 2023

That would be great! My proposal is that there is a new repository called "Skywork-13B-Base-Intermediate" where every checkpoint saved as a different branch in one repo. https://huggingface.co/EleutherAI/pythia-70m That would be a great effort to make a good alternative to Pythia. If it's saved and not critical to anything Huggingface storage is free anyways so might as well put all you have. Just my opinion. Thank you for responding!

Hi there, we have uploaded intermediate checkpoints in the following repo: https://huggingface.co/Skywork/Skywork-13B-Base-Intermediate.
Hope that helps!

puffy310

Nov 22, 2023

I deeply appreciate the release of these intermediate checkpoints and I am excited to use them for research. Thank you for working with me and generally the community to make AI transparent and open as it always should be.

puffy310 changed discussion status to closed Nov 22, 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