climatebert/environmental-claims

Puedes usar el modelo con un pipeline para la clasificación de texto:

from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
from transformers.pipelines.pt_utils import KeyDataset
import datasets
from tqdm.auto import tqdm

dataset_name = 'climatebert/environmental_claims'
model_name = 'climatebert/environmental-claims'

# Si deseas utilizar tus propios datos, simplemente cárgalos como un dataset de 🤗 Datasets, ver https://huggingface.co/docs/datasets/loading
dataset = datasets.load_dataset(dataset_name, split='test')

model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name, max_len=512)

pipe = pipeline('text-classification', model=model, tokenizer=tokenizer, device=0)

# Ver https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.pipeline
for out in tqdm(pipe(KeyDataset(dataset, 'text'), padding=True, truncation=True)):
    print(out)