README.md

metadata

language: en
tags:
  - sarcasm
  - classification
  - gpt-neo
license: mit

GPT-Neo Sarcasm Classifier

This is a fine-tuned version of EleutherAI/gpt-neo-1.3B for detecting sarcasm in text.
It classifies input text as:

• 0 → Not Sarcastic
• 1 → Sarcastic

Intended Use

This model can be used to detect sarcastic comments or headlines for applications such as:

• Social media analysis
• Sentiment enhancement pipelines
• Chatbots that need sarcasm awareness

It works best on text similar to the dataset it was fine-tuned on (sarcasm.csv).

How to Use

You can load and use the model in Python as follows:

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model = "EleutherAI/gpt-neo-1.3B"
adapter_repo = "ke7innn/gpt-neo-sarcasm-base-classification"

tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto")
model = PeftModel.from_pretrained(model, adapter_repo)