File size: 1,664 Bytes
8fe2ba2 35a07ed 8fe2ba2 35a07ed 8fe2ba2 35a07ed 8fe2ba2 35a07ed 8fe2ba2 35a07ed 8fe2ba2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
from unsloth import FastLanguageModel
import torch
import streamlit as st
from transformers import TextStreamer
@st.cache_resource
def load_model():
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "lora_model",
max_seq_length = 2048,
dtype = None,
load_in_4bit = True,
)
FastLanguageModel.for_inference(model)
return model, tokenizer
model, tokenizer = load_model()
st.title("Activity and Emission Prediction")
st.write("Match the potential use case with the corresponding activity and emission values based on provided context.")
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:
{}"""
instruction = st.text_input("Instruction", "Match the potential use case with the corresponding activity and emission values based on the provided context.")
input_text = st.text_area("Input", "Doğal Gaz Kullanımı, Gaz Faturası Yönetimi, Isınma Maliyetleri, Enerji Tasarrufu, Gaz Dağıtımı")
# Button to trigger model generation
if st.button("Generate Response"):
with st.spinner("Generating response..."):
# Prepare inputs for the model
formatted_prompt = alpaca_prompt.format(instruction, input_text, "")
inputs = tokenizer([formatted_prompt], return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=128)
response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
st.write("### Response")
st.write(response_text) |