Instructions to use nlpctx/codet5-java-optimizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nlpctx/codet5-java-optimizer with Transformers:

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

pipe = pipeline("text-generation", model="nlpctx/codet5-java-optimizer")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("nlpctx/codet5-java-optimizer")
model = AutoModelForSeq2SeqLM.from_pretrained("nlpctx/codet5-java-optimizer")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nlpctx/codet5-java-optimizer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nlpctx/codet5-java-optimizer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nlpctx/codet5-java-optimizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nlpctx/codet5-java-optimizer

SGLang

How to use nlpctx/codet5-java-optimizer 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 "nlpctx/codet5-java-optimizer" \
    --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": "nlpctx/codet5-java-optimizer",
		"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 "nlpctx/codet5-java-optimizer" \
        --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": "nlpctx/codet5-java-optimizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nlpctx/codet5-java-optimizer with Docker Model Runner:
```
docker model run hf.co/nlpctx/codet5-java-optimizer
```

codet5-java-optimizer / README.md

Unknown Haas

Fix pipeline_tag to text-generation

ae11703 10 days ago

preview code

raw

history blame contribute delete

3.66 kB

	---
	language: en
	license: apache-2.0
	library_name: transformers
	tags:
	- code
	- java
	- codet5
	- optimization
	- code-generation
	datasets:
	- nlpctx/java_optimisation
	base_model: Salesforce/codet5-small
	pipeline_tag: text-generation
	model-index:
	- name: codet5-java-optimizer
	results: []
	---

	# CodeT5-small Java Optimization Model

	A fine-tuned [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) model for Java code optimization tasks.

	- Model: [nlpctx/codet5-java-optimizer](https://huggingface.co/nlpctx/codet5-java-optimizer)
	- Dataset: [nlpctx/java_optimisation](https://huggingface.co/datasets/nlpctx/java_optimisation)
	- Base Model: [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small)

	## Overview

	This repository contains a fine-tuned CodeT5-small model specifically trained for Java code optimization. The model takes verbose or inefficient Java code and generates more optimal versions.

	## Model Information

	- Base Model: Salesforce/codet5-small
	- Training Dataset: [nlpctx/java_optimisation](https://huggingface.co/datasets/nlpctx/java_optimisation)
	- Framework: HuggingFace Transformers with Seq2SeqTrainer
	- Training Setup: Dual-GPU DataParallel (Kaggle T4×2)
	- Dataset Size: ~6K training / 680 validation Java optimization pairs
	- Optimization Focus: Java code refactoring and performance improvements

	## Files

	- `config.json` - Model configuration
	- `generation_config.json` - Generation parameters
	- `model.safetensors` - Model weights (safetensors format)
	- `merges.txt` - BPE merges file
	- `special_tokens_map.json` - Special tokens mapping
	- `tokenizer_config.json` - Tokenizer configuration
	- `vocab.json` - Vocabulary file

	## Usage

	```python
	from transformers import T5ForConditionalGeneration, RobertaTokenizer
	import torch

	# Load model and tokenizer
	model = T5ForConditionalGeneration.from_pretrained("nlpctx/codet5-java-optimizer")
	tokenizer = RobertaTokenizer.from_pretrained("nlpctx/codet5-java-optimizer")

	# Prepare input Java code
	java_code = "your Java code here"
	input_ids = tokenizer(java_code, return_tensors="pt").input_ids

	# Generate optimized code
	with torch.no_grad():
	outputs = model.generate(
	input_ids,
	max_length=512,
	num_beams=4,
	early_stopping=True
	)

	optimized_code = tokenizer.decode(outputs[0], skip_special_tokens=True)
	print(optimized_code)
	```

	## Example Optimizations

	The model has been trained to recognize and optimize common Java patterns:

	- Switch Expressions: Converting verbose switch statements to switch expressions
	- Collection Operations: Replacing manual iterator removal with `removeIf()`
	- String Handling: Optimizing string concatenation with `StringBuilder`
	- Loop Optimizations: Improving iterative constructs
	- And more...

	## Training Details

	The model was fine-tuned using:
	- Base Model: Salesforce/codet5-small
	- Dataset: nlpctx/java_optimisation from Hugging Face
	- Training Framework: Seq2SeqTrainer with DataParallel
	- Hardware: Kaggle T4×2 (dual GPU)
	- Approach: Standard supervised fine-tuning on Java optimization pairs

	## License

	This model is licensed under the Apache 2.0 license, matching the original [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) model.

	## Acknowledgements

	- Model based on [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small)
	- Training data from [nlpctx/java_optimisation](https://huggingface.co/datasets/nlpctx/java_optimisation) dataset
	- Built with [HuggingFace Transformers](https://github.com/huggingface/transformers)