app.py

import streamlit as st
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline


import logging, sys
from dotenv import load_dotenv


from huggingface_hub import login
#load_dotenv()

#HF_TOKEN  = os.environ.get("HF_API_TOKEN")
HF_TOKEN = st.secrets["HF_API_TOKEN"]
login(token=HF_TOKEN)

# Setup logging
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

 

#model_id = "meta-llama/Meta-Llama-3-8B"
model_id = "mistralai/Mistral-7B-v0.1"



#tokenizer = AutoTokenizer.from_pretrained(model_id)
#model = AutoModelForCausalLM.from_pretrained(model_id)

# Create text generation pipeline
#pipe = pipeline(model = model_id)
pipe = pipeline('text-generation', model=model_id)

with st.form('my_form'):
    question = st.text_area('Enter your question:', 'Tell me about attention mechanisms in a transformer?')
    submitted = st.form_submit_button('Submit')
    if submitted:
        result = pipe(question, max_length=100)
        st.write(question)
        st.write(result)