Text Generation
Transformers
Safetensors
mt5
feature-extraction
headline-generation
tags-generation
multilingual
text2text-generation
Instructions to use faisaltareque/XL-HeadTags-mT5-c5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use faisaltareque/XL-HeadTags-mT5-c5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="faisaltareque/XL-HeadTags-mT5-c5")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("faisaltareque/XL-HeadTags-mT5-c5") model = AutoModel.from_pretrained("faisaltareque/XL-HeadTags-mT5-c5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use faisaltareque/XL-HeadTags-mT5-c5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "faisaltareque/XL-HeadTags-mT5-c5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "faisaltareque/XL-HeadTags-mT5-c5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/faisaltareque/XL-HeadTags-mT5-c5
- SGLang
How to use faisaltareque/XL-HeadTags-mT5-c5 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 "faisaltareque/XL-HeadTags-mT5-c5" \ --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": "faisaltareque/XL-HeadTags-mT5-c5", "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 "faisaltareque/XL-HeadTags-mT5-c5" \ --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": "faisaltareque/XL-HeadTags-mT5-c5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use faisaltareque/XL-HeadTags-mT5-c5 with Docker Model Runner:
docker model run hf.co/faisaltareque/XL-HeadTags-mT5-c5
|
Download README.md from faisaltareque/XL-HeadTags-mT5-c5: direct link, hf CLI and curl.
- Browser
- Download file 6.27 kB
-
https://huggingface.co/faisaltareque/XL-HeadTags-mT5-c5/resolve/main/README.md
- Command line
-
hf download hf://faisaltareque/XL-HeadTags-mT5-c5/README.md
-
curl -L -o README.md https://huggingface.co/faisaltareque/XL-HeadTags-mT5-c5/resolve/main/README.md
6.27 kB
metadata
library_name: transformers
tags:
- headline-generation
- tags-generation
- multilingual
license: cc-by-sa-4.0
datasets:
- faisaltareque/XL-HeadTags
pipeline_tag: text2text-generation
Model Card for Model ID
This is a Text-to-Text model for generating headlines and tags from news articles.
Model Details
Model Description
This model is a Text-to-Text model for generating headlines and tags from news articles. This is a mT5 model finetuned on the XL-HeadTags multilingual dataset (read more).
- Model type: T5
- Finetuned from model : mT5
Model Sources [optional]
- Repository: XL-HeadTags
- Paper: XL-HeadTags
Citation [optional]
@inproceedings{shohan-etal-2024-xl,
title = "{XL}-{H}ead{T}ags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags",
author = "Shohan, Faisal and
Nayeem, Mir Tafseer and
Islam, Samsul and
Akash, Abu Ubaida and
Joty, Shafiq",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.771",
pages = "12991--13024"
}
Model Card Authors [optional]
- Faisal Tareque Shohan (faisaltareque@hotmail.com)
- Mir Tafseer Nayeem (mnayeem@ualberta.ca)
- Samsul Islam (samsulratul98@gmail.com)
- Abu Ubaida Akash (abu.ubaida.akash@usherbrooke.ca)
- Shafiq Joty (sjoty@salesforce.com)