Text Generation
Transformers
PyTorch
Southern Ndebele
English
m2m_100
text2text-generation
m2m100
translation
africanlp
african
ndebele
Instructions to use dsfsi/nr-en-m2m100-gov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dsfsi/nr-en-m2m100-gov with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dsfsi/nr-en-m2m100-gov")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("dsfsi/nr-en-m2m100-gov") model = AutoModelForSeq2SeqLM.from_pretrained("dsfsi/nr-en-m2m100-gov", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dsfsi/nr-en-m2m100-gov with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dsfsi/nr-en-m2m100-gov" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dsfsi/nr-en-m2m100-gov", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dsfsi/nr-en-m2m100-gov
- SGLang
How to use dsfsi/nr-en-m2m100-gov 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 "dsfsi/nr-en-m2m100-gov" \ --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": "dsfsi/nr-en-m2m100-gov", "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 "dsfsi/nr-en-m2m100-gov" \ --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": "dsfsi/nr-en-m2m100-gov", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dsfsi/nr-en-m2m100-gov with Docker Model Runner:
docker model run hf.co/dsfsi/nr-en-m2m100-gov
| license: cc-by-4.0 | |
| language: | |
| - nr | |
| - en | |
| pipeline_tag: text2text-generation | |
| tags: | |
| - m2m100 | |
| - translation | |
| - africanlp | |
| - african | |
| - ndebele | |
| # [nr-en] South Ndebele to English Translation Model based on M2M100 and The South African Gov-ZA multilingual corpus | |
| Model created from South Ndebele to English aligned sentences from [The South African Gov-ZA multilingual corpus](https://github.com/dsfsi/gov-za-multilingual) | |
| The data set contains cabinet statements from the South African government, maintained by the Government Communication and Information System (GCIS). Data was scraped from the governments website: https://www.gov.za/cabinet-statements | |
| ## Authors | |
| - Vukosi Marivate - [@vukosi](https://twitter.com/vukosi) | |
| - Matimba Shingange | |
| - Richard Lastrucci | |
| - Isheanesu Joseph Dzingirai | |
| - Jenalea Rajab | |
| ## BibTeX entry and citation info | |
| ``` | |
| @inproceedings{lastrucci-etal-2023-preparing, | |
| title = "Preparing the Vuk{'}uzenzele and {ZA}-gov-multilingual {S}outh {A}frican multilingual corpora", | |
| author = "Richard Lastrucci and Isheanesu Dzingirai and Jenalea Rajab and Andani Madodonga and Matimba Shingange and Daniel Njini and Vukosi Marivate", | |
| booktitle = "Proceedings of the Fourth workshop on Resources for African Indigenous Languages (RAIL 2023)", | |
| month = may, | |
| year = "2023", | |
| address = "Dubrovnik, Croatia", | |
| publisher = "Association for Computational Linguistics", | |
| url = "https://aclanthology.org/2023.rail-1.3", | |
| pages = "18--25" | |
| } | |
| ``` | |
| [Paper - Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corpora](https://arxiv.org/abs/2303.03750) | |