app.py

# Load model directly
import streamlit as st
from unsloth import FastLanguageModel
import torch
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "shivam9980/mistral-7b-news-cnn-merged", # Choose ANY! eg teknium/OpenHermes-2.5-Mistral-7B
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    token = hf_token, # use one if using gated models like meta-llama/Llama-2-7b-hf
)

# alpaca_prompt = You MUST copy from above!

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:
{}"""

  # alpaca_prompt = Copied from above
c = st.text_input('Enter the contents ')
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
inputs = tokenizer(
[
    alpaca_prompt.format(
        "The following passage is content from a news report. Please summarize this passage in one sentence or less.", # instruction
        c,
        "", # 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)
out = results[0].split('\n')[-1]
st.text_area(label='Headline',value=out[:])