File size: 1,287 Bytes
d0452d9 cbc5205 3cf1317 d0452d9 c416b4a d0452d9 c416b4a d0452d9 2d38204 d0452d9 4b4029b a2f1380 d0452d9 c416b4a d0452d9 c416b4a 09c9222 c416b4a 4b4029b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
peft_model_id = f"alimrb/eff24-new"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(
config.base_model_name_or_path,
return_dict=True,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id)
def make_inference(question, answer):
batch = tokenizer(
f"### Question:\n{question}\n\n### Answer:",
return_tensors="pt",
)
# Move batch to the same device as the model
batch = {k: v.to(model.device) for k, v in batch.items()}
with torch.cuda.amp.autocast():
output_tokens = model.generate(**batch, max_new_tokens=50)
return tokenizer.decode(output_tokens[0], skip_special_tokens=True)
if __name__ == "__main__":
# Create a Gradio interface
import gradio as gr
gr.Interface(
make_inference,
[
gr.Textbox(lines=2, label="Question"),
],
gr.Textbox(label="Answer"),
title="EFF24",
description="EFF24 is a generative model that generates Answers for Questions."
).launch()
|