Spaces:
Runtime error
Runtime error
import streamlit as st | |
from PIL import Image | |
import streamlit as st | |
from transformers import pipeline | |
import pandas as pd | |
import plotly.express as px | |
import matplotlib.pyplot as plt | |
from pathlib import Path | |
import base64 | |
from st_pages import Page, add_page_title, show_pages | |
from streamlit_extras.badges import badge | |
import transformers | |
model_name = 'Intel/neural-chat-7b-v3-1' | |
model = transformers.AutoModelForCausalLM.from_pretrained(model_name) | |
tokenizer = transformers.AutoTokenizer.from_pretrained(model_name) | |
def generate_response(system_input, user_input): | |
# Format the input using the provided template | |
prompt = f"### System:\n{system_input}\n### User:\n{user_input}\n### Assistant:\n" | |
# Tokenize and encode the prompt | |
inputs = tokenizer.encode(prompt, return_tensors="pt", add_special_tokens=False) | |
# Generate a response | |
outputs = model.generate(inputs, max_length=1000, num_return_sequences=1) | |
response = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
# Extract only the assistant's response | |
return response.split("### Assistant:\n")[-1] | |
# Example usage | |
system_input = "You are a employee in the customer succes department of a company called Retraced that works in sustainability and traceability" | |
prompt = st.text_input(str("Insert here you prompt?")) | |
response = generate_response(system_input, prompt) | |
st.write(response) | |