DeBERTa-v3-large-mnli-fever-anli-ling-wanli

import torch
import argparse
from openmind import pipeline, is_torch_npu_available
import time

def parse_args():
    parser = argparse.ArgumentParser(description="Eval the model")
    parser.add_argument(
       "--model_name_or_path",
       type=str,
       help="path or model",
       default="JeffDing/DeBERTa-v3-large-mnli-fever-anli-ling-wanli",
    )
    args = parser.parse_args()
    return args


def main():
    args = parse_args()
    model_path = args.model_name_or_path

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

    classifier = pipeline("zero-shot-classification", model=model_path,device_map=device)

    sequence_to_classify = "Angela Merkel ist eine Politikerin in Deutschland und Vorsitzende der CDU"
    candidate_labels = ["politics", "economy", "entertainment", "environment"]
    output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
    print(output)

    end_time = time.time()
    print(f"硬件环境：{device},推理执行时间：{end_time - start_time}秒")

if __name__ == "__main__":
   main()

from transformers import pipeline
classifier = pipeline("zero-shot-classification", model="MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli")
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)

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")

model_name = "MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

premise = "I first thought that I liked the movie, but upon second thought it was actually disappointing."
hypothesis = "The movie was not 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=4,              # total number of training epochs
    learning_rate=5e-06,
    per_device_train_batch_size=16,   # batch size per device during training
    gradient_accumulation_steps=2,    # doubles the effective batch_size to 32, while decreasing memory requirements
    per_device_eval_batch_size=64,    # batch size for evaluation
    warmup_ratio=0.06,                # number of warmup steps for learning rate scheduler
    weight_decay=0.01,               # strength of weight decay
    fp16=True                        # mixed precision training
)