Instructions to use NinedayWang/PolyCoder-0.4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NinedayWang/PolyCoder-0.4B with Transformers:

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

pipe = pipeline("text-generation", model="NinedayWang/PolyCoder-0.4B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NinedayWang/PolyCoder-0.4B")
model = AutoModelForCausalLM.from_pretrained("NinedayWang/PolyCoder-0.4B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NinedayWang/PolyCoder-0.4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NinedayWang/PolyCoder-0.4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NinedayWang/PolyCoder-0.4B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NinedayWang/PolyCoder-0.4B

SGLang

How to use NinedayWang/PolyCoder-0.4B 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 "NinedayWang/PolyCoder-0.4B" \
    --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": "NinedayWang/PolyCoder-0.4B",
		"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 "NinedayWang/PolyCoder-0.4B" \
        --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": "NinedayWang/PolyCoder-0.4B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NinedayWang/PolyCoder-0.4B with Docker Model Runner:
```
docker model run hf.co/NinedayWang/PolyCoder-0.4B
```

PolyCoder-0.4B / README.md

NinedayWang

Update README.md (#2)

f1b0479 over 3 years ago

preview code

raw

history blame contribute delete

894 Bytes

	This is a PolyCoder model with 0.4B parameters,
	presented in the paper ["A Systematic Evaluation of Large Language Models of Code"](https://arxiv.org/pdf/2202.13169.pdf) (MAPS'2022 and ICLR'2022 Workshop Deep Learning 4 Code).

	The model was trained on 249 GB of code across 12 programming languages.

	Note - this model requires `transformers` version of at least 4.23.0:
	```
	pip install transformers==4.23.0
	```
	For more information, see: [https://github.com/VHellendoorn/Code-LMs](https://github.com/VHellendoorn/Code-LMs)

	If you use this model, please cite:
	```
	@inproceedings{
	xu2022polycoder,
	title={A Systematic Evaluation of Large Language Models of Code},
	author={Frank F. Xu and Uri Alon and Graham Neubig and Vincent Josua Hellendoorn},
	booktitle={Deep Learning for Code Workshop},
	year={2022},
	url={https://openreview.net/forum?id=SLcEnoObJZq}
	}
	```