Text Generation
Transformers
Safetensors
starcoder2
code
Eval Results (legacy)
text-generation-inference
Instructions to use bigcode/starcoder2-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigcode/starcoder2-3b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigcode/starcoder2-3b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigcode/starcoder2-3b") model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-3b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigcode/starcoder2-3b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigcode/starcoder2-3b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigcode/starcoder2-3b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigcode/starcoder2-3b
- SGLang
How to use bigcode/starcoder2-3b 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/starcoder2-3b" \ --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/starcoder2-3b", "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/starcoder2-3b" \ --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/starcoder2-3b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigcode/starcoder2-3b with Docker Model Runner:
docker model run hf.co/bigcode/starcoder2-3b
Request on prompts for the evaluation results.
#5
by sh0416 - opened
I reproduced the result for MBPP+ and the reproduced score is 0.4385, which is different from the reported score (0.474).
I think the difference comes from the prompt that I've used for my experiment.
My prompt is as follow.
Problem: Write a function to find the shared elements from the given two lists.
Test:
assert set(similar_elements((3, 4, 5, 6),(5, 7, 4, 10))) == set((4, 5))
assert set(similar_elements((1, 2, 3, 4),(5, 4, 3, 7))) == set((3, 4))
assert set(similar_elements((11, 12, 14, 13),(17, 15, 14, 13))) == set((13, 14))
Implementation:
```python
What is the prompt for the evaluation?
Thank you