Instructions to use microsoft/CodeGPT-small-java with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/CodeGPT-small-java with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/CodeGPT-small-java")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/CodeGPT-small-java")
model = AutoModelForCausalLM.from_pretrained("microsoft/CodeGPT-small-java", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/CodeGPT-small-java with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/microsoft/CodeGPT-small-java

SGLang

How to use microsoft/CodeGPT-small-java 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 "microsoft/CodeGPT-small-java" \
    --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": "microsoft/CodeGPT-small-java",
		"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 "microsoft/CodeGPT-small-java" \
        --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": "microsoft/CodeGPT-small-java",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use microsoft/CodeGPT-small-java with Docker Model Runner:
```
docker model run hf.co/microsoft/CodeGPT-small-java
```

CodeGPT-small-java

Commit History

Sep 9, 2020

12:34
Update tokenizer_config.json

system HF Staff

6d6b0ee
12:34
Update vocab.json

system HF Staff

e9de4a2
12:34
Update special_tokens_map.json

system HF Staff

dcdd65c
12:34
Update pytorch_model.bin

system HF Staff

a60249e
12:34
Update merges.txt

system HF Staff

fadfd2b
12:34
Update tf_model.h5

system HF Staff

5330683
12:34
initial commit

system HF Staff

ba4c6eb

Commit History

Sep 9, 2020

Update tokenizer_config.json

Update vocab.json

Update special_tokens_map.json

Update pytorch_model.bin

Update merges.txt

Update tf_model.h5

initial commit