Finetuning / inference.py

Upload 10 files

57eb232 verified about 2 months ago

973 Bytes

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

MODEL_PATH = "."

tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_PATH)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

def ask_resume_bot(question):
    prompt = f"Answer this resume question: {question}"
    inputs = tokenizer(prompt, return_tensors="pt", truncation=True).to(device)

    with torch.no_grad():
        output = model.generate(
            **inputs,
            max_new_tokens=100,
            num_beams=4
        )

    return tokenizer.decode(output[0], skip_special_tokens=True)

if __name__ == "__main__":
    questions = [
        "What is your educational background?",
        "What are your technical skills?",
        "Tell me about your medical X-ray project."
    ]

    for q in questions:
        print("Q:", q)
        print("A:", ask_resume_bot(q))
        print()

	from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
	import torch

	MODEL_PATH = "."

	tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
	model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_PATH)

	device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
	model.to(device)

	def ask_resume_bot(question):
	prompt = f"Answer this resume question: {question}"
	inputs = tokenizer(prompt, return_tensors="pt", truncation=True).to(device)

	with torch.no_grad():
	output = model.generate(
	**inputs,
	max_new_tokens=100,
	num_beams=4
	)

	return tokenizer.decode(output[0], skip_special_tokens=True)

	if __name__ == "__main__":
	questions = [
	"What is your educational background?",
	"What are your technical skills?",
	"Tell me about your medical X-ray project."
	]

	for q in questions:
	print("Q:", q)
	print("A:", ask_resume_bot(q))
	print()