Downloads · 30 days
5
5% of all-time downloads
kishankachhadiya/debarta-text-classifier-v1
debarta-text-classifier-v1 is a text classification model from kishankachhadiya. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
This model is fine-tuned on a labeled dataset for AI-generated vs. Human-written text detection.
Downloads · 30 days
5
5% of all-time downloads
All-time downloads
103
Public
Parameters
435M
7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.7 GB · 99%
From the Hugging Face model README
This model is fine-tuned on a labeled dataset for AI-generated vs. Human-written text detection.
microsoft/deberta-v3-large| Metric | Score |
|---|---|
| Accuracy | 0.982 |
| Human (0) – Precision | 0.976 |
| Human (0) – Recall | 0.987 |
| AI (1) – Precision | 0.987 |
| AI (1) – Recall | 0.976 |

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
tokenizer = AutoTokenizer.from_pretrained("kishankachhadiya/debarta-text-classifier-v1")
model = AutoModelForSequenceClassification.from_pretrained("kishankachhadiya/debarta-text-classifier-v1")
text = "This text was likely written by an AI model."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
probs = torch.nn.functional.softmax(outputs.logits, dim=1)
print(probs)