AquilaX-AI/QnA-2

INFERENCE

import time
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

finetuned_model = AutoModelForCausalLM("AquilaX-AI/QnA-2")
tokenizer = AutoTokenizer("AquilaX-AI/QnA-2")

alpaca_prompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
what is machine learning?

### Response:
"""

s = time.time()
prompt = alpaca_prompt
encodeds = tokenizer(prompt, return_tensors="pt",truncation=True).input_ids

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
finetuned_model.to(device)
inputs = encodeds.to(device)

# Increase max_new_tokens if needed
generated_ids = finetuned_model.generate(inputs, max_new_tokens=256, temperature=0.5, top_p=0.90, do_sample=True,pad_token_id=50259,eos_token_id=50259,num_return_sequences=1)
print(tokenizer.decode(generated_ids[0]).split('### Response:')[1].split('<eos>')[0].strip())
e = time.time()
print(f'time taken:{e-s}')