RAG_Qwen / app.py
AdityaShingote's picture
Create app.py
88301ec verified
raw
history blame
780 Bytes
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
# Load the model and tokenizer
model_name = "Qwen/Qwen1.5-7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
def generate_article(topic):
inputs = tokenizer(f"Generate article for the NY times tweet {topic}", return_tensors="pt")
outputs = model.generate(inputs['input_ids'], max_new_tokens=512, temperature=0.5)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
# Create the Gradio interface
iface = gr.Interface(
fn=generate_article,
inputs="text",
outputs="text",
title="Article Generator",
description="Generate an article for a given topic."
)
# Launch the Gradio app
iface.launch()