Downloads · 30 days
14
3% of all-time downloads
AutoTrain-LUC-COMP429-VEAA-Classification
NicholasSynovic/AutoTrain-LUC-COMP429-VEAA-Classification
AutoTrain-LUC-COMP429-VEAA-Classification is a text classification model from NicholasSynovic. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as agpl-3.0.
- Problem type: Multi-class Classification - Model ID: 52472123757 - CO2 Emissions (in grams): 4.1360
All-time downloads
449
Public
Parameters
110M
877 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 50%
Parameter types
How the weights are stored.
F32110M · 100%
Try a prompt
Model card
From the Hugging Face model README
Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 52472123757
- CO2 Emissions (in grams): 4.1360
This model reuses and extends a Bert model trained on NicholasSynovic/Free-AutoTrain-VEAA
Validation Metrics
- Loss: 1.425
- Accuracy: 0.636
- Macro F1: 0.504
- Micro F1: 0.636
- Weighted F1: 0.624
- Macro Precision: 0.523
- Micro Precision: 0.636
- Weighted Precision: 0.630
- Macro Recall: 0.508
- Micro Recall: 0.636
- Weighted Recall: 0.636
Usage
You can use cURL to access this model:
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/NicholasSynovic/autotrain-luc-comp429-victorian-authorship-classification-52472123757
Or Python API:
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("NicholasSynovic/AutoTrain-LUC-COMP429-VEAA-Classification", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("NicholasSynovic/autotrain-luc-comp429-victorian-authorship-classification-52472123757", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- agpl-3.0
- Languages
- en
- Created
- Apr 25, 2023
- Updated
- Jul 28, 2023