Instructions to use Anshul2000s/twitter_suicide_detection_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Anshul2000s/twitter_suicide_detection_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Anshul2000s/twitter_suicide_detection_model")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Anshul2000s/twitter_suicide_detection_model") model = AutoModelForSequenceClassification.from_pretrained("Anshul2000s/twitter_suicide_detection_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
twitter_suicide_detection_model
BERT model fine-tuned to determine whether Twitter posts are potentially suicidal.
I used Huggingface libraries to perform the fine-tuning.
Format of prompt
prompt = "Is this post potentially suicidal: " + tweet
Before Use
Use the above format to generate the most accurate completions.
Completion
0 = " Not a suicidal post ", 1 = " Potentially Suicidal "
Training/Test split and other information
80:20 % Epochs = 1
I want to be able to run this on a GPU and acquire more training data as well.
This model is in the hugging face repository:
https://huggingface.co/Anshul2000s/twitter_suicide_detection_model
- Downloads last month
- 7