Instructions to use AUEB-NLP/ByT5_g2g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AUEB-NLP/ByT5_g2g with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AUEB-NLP/ByT5_g2g")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("AUEB-NLP/ByT5_g2g") model = AutoModelForSeq2SeqLM.from_pretrained("AUEB-NLP/ByT5_g2g") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AUEB-NLP/ByT5_g2g with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AUEB-NLP/ByT5_g2g" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AUEB-NLP/ByT5_g2g", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AUEB-NLP/ByT5_g2g
- SGLang
How to use AUEB-NLP/ByT5_g2g 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 "AUEB-NLP/ByT5_g2g" \ --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": "AUEB-NLP/ByT5_g2g", "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 "AUEB-NLP/ByT5_g2g" \ --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": "AUEB-NLP/ByT5_g2g", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AUEB-NLP/ByT5_g2g with Docker Model Runner:
docker model run hf.co/AUEB-NLP/ByT5_g2g
ByT5 Greeklish to Greek Conversion Model
Model Overview
This model is a finetuned version of the ByT5 transformer model specifically trained to convert Greeklish (Greek written with Latin characters) to Greek (Greek written with Greek characters). The base model, ByT5, is a variant of the T5 model that operates directly on byte sequences, making it particularly well-suited for tasks involving text written in non-standard forms or using non-standard characters.
Model Details
- Model Name: ByT5_g2g
- Model Architecture: ByT5
- Finetuned for Task: Greeklish to Greek Transliteration
Model Sources
Paper: Toumazatos, A., Pavlopoulos, J., Androutsopoulos, I., & Vassos, S. (2024). Still All Greeklish to Me: Greeklish to Greek Transliteration. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) (pp. 15309–15319). ELRA and ICCL.
Repository: https://github.com/nlpaueb/greeklish
Points of contact: spirosbarbakos@gmail.com, tatoumazatos@gmail.com
- Downloads last month
- 874