Instructions to use SkyworkAIGC/SkyCode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SkyworkAIGC/SkyCode with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SkyworkAIGC/SkyCode")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SkyworkAIGC/SkyCode") model = AutoModelForCausalLM.from_pretrained("SkyworkAIGC/SkyCode") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SkyworkAIGC/SkyCode with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SkyworkAIGC/SkyCode" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SkyworkAIGC/SkyCode", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SkyworkAIGC/SkyCode
- SGLang
How to use SkyworkAIGC/SkyCode 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 "SkyworkAIGC/SkyCode" \ --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": "SkyworkAIGC/SkyCode", "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 "SkyworkAIGC/SkyCode" \ --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": "SkyworkAIGC/SkyCode", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SkyworkAIGC/SkyCode with Docker Model Runner:
docker model run hf.co/SkyworkAIGC/SkyCode
Trying huggingface API Failed, please help.
import requests
API_URL = "https://api-inference.huggingface.co/models/SkyWork/SkyCode"
headers = {"Authorization": "Bearer hf_........................................."}
def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
return response.json()
output = query({
"inputs": "if __name__ == ",
})
print(output)
{'error': "Can't load tokenizer using from_pretrained, please update its configuration: Loading SkyWork/SkyCode requires you to execute the tokenizer file in that repo on your local machine. Make sure you have read the code there to avoid malicious use, then set the option trust_remote_code=True to remove this error."}
Sorry, current the Sky models are not available via hugging-face API. Feel Free to Get the model parameters via:
from transformers import GPT2LMHeadModel
from transformers import AutoTokenizer
model = GPT2LMHeadModel.from_pretrained("SkyWork/SkyCode")
tokenizer = AutoTokenizer.from_pretrained("SkyWork/SkyCode", trust_remote_code=True)