Instructions to use yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm with Transformers:

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

pipe = pipeline("text-generation", model="yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm")
model = AutoModelForCausalLM.from_pretrained("yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm

SGLang

How to use yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm 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 "yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm" \
    --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": "yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm",
		"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 "yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm" \
        --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": "yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm with Docker Model Runner:
```
docker model run hf.co/yanghuattt/microsoft_CodeGPT-small-java_0_ft_clm
```

microsoft_CodeGPT-small-java_0_ft_clm / data_args.json

yanghuattt

Training in progress, step 500

3280678 verified 11 months ago

raw

history blame

485 Bytes

	{
	"dataset_name": null,
	"dataset_config_name": null,
	"train_file": "/home/hyang45/se_git_repo/final_addtional_exp_mia_trans/datasetws/rule_0.txt",
	"validation_file": "/home/hyang45/se_git_repo/final_addtional_exp_mia_trans/datasetws/prep_dev.txt",
	"max_train_samples": null,
	"max_eval_samples": null,
	"streaming": false,
	"block_size": 1024,
	"overwrite_cache": false,
	"validation_split_percentage": 5,
	"preprocessing_num_workers": null,
	"keep_linebreaks": true
	}