SocRoBERTa-base 模型卡片

from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
import argparse
from openmind_hub import snapshot_download


def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="",
        default="Jinan_AICC/SocRoBERTa-base",
    )
    args = parser.parse_args()
    return args

args = parse_args()
modelname = args.model_name_or_path

tokenizer_name = modelname
if args.model_name_or_path:
    modelname = args.model_name_or_path
else:
    modelname = snapshot_download(
        "Jinan_AICC/SocRoBERTa-base",
        revision="main",
        ignore_patterns=["*.h5", "*.ot", "*.msgpack"],       
    )

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

pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)

print(pipe("Scope 1 emissions are reported here on a like-for-like basis against the 2013 baseline and exclude emissions from additional vehicles used during repairs.", padding=True, truncation=True))