Text Generation
Transformers
Safetensors
Yiddish
English
t5
text2text-generation
yiddish
transliteration
text-generation-inference
Instructions to use shoowadoo/galkhesnet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shoowadoo/galkhesnet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="shoowadoo/galkhesnet")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("shoowadoo/galkhesnet") model = AutoModelForSeq2SeqLM.from_pretrained("shoowadoo/galkhesnet") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use shoowadoo/galkhesnet with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "shoowadoo/galkhesnet" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shoowadoo/galkhesnet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/shoowadoo/galkhesnet
- SGLang
How to use shoowadoo/galkhesnet 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 "shoowadoo/galkhesnet" \ --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": "shoowadoo/galkhesnet", "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 "shoowadoo/galkhesnet" \ --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": "shoowadoo/galkhesnet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use shoowadoo/galkhesnet with Docker Model Runner:
docker model run hf.co/shoowadoo/galkhesnet
My ByT5 Fine-Tuned Model
Model description
This is a fine-tuned version of google/byt5-small.
It was trained on my custom dataset for transliterating Yiddish characters to Latin characters.
Intended uses & limitations
- Intended use: transliteration
Training data
Transliterated Wiktionary data and Bible verses were used for model development.
How to use
Load with ๐ค Transformers:
from transformers import pipeline
transliterator = pipeline("text-generation", model="shoowadoo/galkhesnet")
transliterator('Your Yiddish word here')[0]['generated_text']
transliterator("Your Yiddish word here", num_beams=10, num_return_sequences=10, max_length=100)
- Downloads last month
- 23
Model tree for shoowadoo/galkhesnet
Base model
google/byt5-small