DeBERTa-v3-base-mnli-fever-anli

import argparse
import torch
from openmind import pipeline, is_torch_npu_available

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        default=None,
        type=str,
        help="Path to model",
        required=False,
    )

    args = parser.parse_args()

    return args

if __name__=="__main__":

    args = parse_args()

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"

    #推理
    classifier = pipeline('zero-shot-classification', model=args.model_name_or_path, device=device)

    sequence_to_classify = "Angela Merkel is a politician in Germany and leader of the CDU"
    candidate_labels = ["politics", "economy", "entertainment", "environment"]
    output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
    print(output)

import argparse
import torch
from openmind import is_torch_npu_available, AutoTokenizer, AutoModelForSequenceClassification

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        default=None,
        type=str,
        help="Path to model",
        required=False,
    )

    args = parser.parse_args()

    return args

if __name__=="__main__":

    args = parse_args()

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"

    #推理
    model_name = args.model_name_or_path
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForSequenceClassification.from_pretrained(model_name).to(device)

    premise = "I first thought that I liked the movie, but upon second thought it was actually disappointing."
    hypothesis = "The movie was good."

    input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
    output = model(input["input_ids"].to(device))  # device = "cuda:0" or "cpu"
    prediction = torch.softmax(output["logits"][0], -1).tolist()
    label_names = ["entailment", "neutral", "contradiction"]
    prediction = {name: round(float(pred) * 100, 1) for pred, name in zip(prediction, label_names)}
    print(prediction)

training_args = TrainingArguments(
    num_train_epochs=3,              # total number of training epochs
    learning_rate=2e-05,
    per_device_train_batch_size=32,   # batch size per device during training
    per_device_eval_batch_size=32,    # batch size for evaluation
    warmup_ratio=0.1,                # number of warmup steps for learning rate scheduler
    weight_decay=0.06,               # strength of weight decay
    fp16=True                        # mixed precision training
)