kaggle-comp-test / README.md
abhishek's picture
abhishek HF staff
Commit From AutoNLP
59f1cac
|
raw
history blame
1.39 kB
---
tags: autonlp
language: en
widget:
- text: "I love AutoNLP 🤗"
datasets:
- Crasher222/autonlp-data-kaggle-test
co2_eq_emissions: 60.744727079482495
---
# Model Trained Using AutoNLP
- Problem type: Multi-class Classification
- Model ID: 25805800
- CO2 Emissions (in grams): 60.744727079482495
## Validation Metrics
- Loss: 0.4422711133956909
- Accuracy: 0.8615328555811976
- Macro F1: 0.8642434650461513
- Micro F1: 0.8615328555811976
- Weighted F1: 0.8617743626671308
- Macro Precision: 0.8649112225076049
- Micro Precision: 0.8615328555811976
- Weighted Precision: 0.8625407179375096
- Macro Recall: 0.8640777539828228
- Micro Recall: 0.8615328555811976
- Weighted Recall: 0.8615328555811976
## 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 AutoNLP"}' https://api-inference.huggingface.co/models/Crasher222/autonlp-kaggle-test-25805800
```
Or Python API:
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("Crasher222/autonlp-kaggle-test-25805800", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("Crasher222/autonlp-kaggle-test-25805800", use_auth_token=True)
inputs = tokenizer("I love AutoNLP", return_tensors="pt")
outputs = model(**inputs)
```