Instructions to use bigcode/starcoderplus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigcode/starcoderplus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigcode/starcoderplus")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigcode/starcoderplus") model = AutoModelForCausalLM.from_pretrained("bigcode/starcoderplus") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use bigcode/starcoderplus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigcode/starcoderplus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigcode/starcoderplus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigcode/starcoderplus
- SGLang
How to use bigcode/starcoderplus 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 "bigcode/starcoderplus" \ --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": "bigcode/starcoderplus", "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 "bigcode/starcoderplus" \ --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": "bigcode/starcoderplus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigcode/starcoderplus with Docker Model Runner:
docker model run hf.co/bigcode/starcoderplus
Why is the HumanEval SCORE LOWER than starcoder and starcoderbase?
#5
by qftie - opened
What's the defference between starcoder/starcoderbase/starcoderplus? Why is the HumanEval SCORE of starcoderplus LOWER than starcoder and starcoderbase?
For StarCoderPlus, we fine-tuned StarCoderBase on a lot of english data (while inclduing The Stack code dataset again), so the model seems to have forgot some coding capabilities. But the trade off between English and code performance seems reasonable.
loubnabnl changed discussion status to closed