|
import gradio as gr |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
model_name = "meta-llama/Llama-2-7b-hf" |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
model = AutoModelForCausalLM.from_pretrained(model_name) |
|
|
|
def generate_response(prompt): |
|
inputs = tokenizer(prompt, return_tensors="pt") |
|
outputs = model.generate(**inputs, max_length=2000, temperature=0.6) |
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
return response |
|
|
|
iface = gr.Interface( |
|
fn=generate_response, |
|
inputs="textbox", |
|
outputs="textbox", |
|
title="LLaMA 2 Chatbot", |
|
description="Ask questions to the LLaMA 2 model" |
|
) |
|
|
|
iface.launch() |
