metadata

library_name: transformers
tags: []

INFERENCE

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import time
import torch

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = AutoModelForSequenceClassification.from_pretrained("Mr-Vicky-01/helping_agent_classification").to(device)
tokenizer = AutoTokenizer.from_pretrained("Mr-Vicky-01/helping_agent_classification")

start = time.time()
question = "show my critical vulns"
print("Question: ", question)
inputs = tokenizer(question, return_tensors="pt").to("cuda")
with torch.no_grad():
    logits = model(**inputs).logits

predicted_class_id = logits.argmax().item()
print("predicted_class: ", model.config.id2label[predicted_class_id])

print("Time_taken: ", time.time() - start)