app.py

# Load model directly
import streamlit as st
from transformers import AutoModel
model,tokenizer = AutoModel.from_pretrained("shivam9980/mistral-7b-news")
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

content = st.text_input('Content')
inputs = tokenizer(
[
    alpaca_prompt.format(
        "The following passage is content from a news report. Please summarize this passage in one sentence or less.", # instruction
        content, # input
        "", # output - leave this blank for generation!
    )
], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
results= tokenizer.batch_decode(outputs)
st.write(results)