File size: 2,535 Bytes
5f3e194 | 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 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 | import streamlit as st
import os
import gdown
from transformers import AutoTokenizer, AutoConfig, AutoModelForSequenceClassification
from safetensors.torch import load_file
import torch
# ================================
# 1. Google Drive FILE ID (model.safetensors)
# ================================
FILE_ID = "1eMR7jxkj5XLLIV6t9IIllpfegxHWCi_A"
MODEL_DIR = "model_folder"
MODEL_FILE = os.path.join(MODEL_DIR, "model.safetensors")
# ================================
# 2. Download model file (jika belum ada)
# ================================
if not os.path.exists(MODEL_DIR):
os.makedirs(MODEL_DIR, exist_ok=True)
if not os.path.exists(MODEL_FILE):
st.write("Mengunduh model.safetensors dari Google Drive...")
url = f"https://drive.google.com/uc?id={FILE_ID}"
gdown.download(url, MODEL_FILE, quiet=False)
st.success("model.safetensors berhasil di-download!")
# ================================
# 3. Load model & tokenizer TANPA META MODE
# ================================
st.write("Memuat model...")
tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)
# 3A — Load config
config = AutoConfig.from_pretrained(MODEL_DIR)
# 3B — Buat model kosong
model = AutoModelForSequenceClassification.from_config(config)
# 3C — Load bobot SAFETENSORS
state_dict = load_file(MODEL_FILE)
model.load_state_dict(state_dict, strict=True)
model.to("cpu")
model.eval()
st.success("Model siap digunakan!")
# ================================
# 4. Label Mapping
# ================================
label_map = {
0: "Negatif",
1: "Positif"
}
# ================================
# 5. Streamlit UI
# ================================
st.title("🚀 Klasifikasi Kalimat dengan Model dari Google Drive")
text = st.text_area("Masukkan kalimat:")
if st.button("Klasifikasi"):
if text.strip() == "":
st.warning("Tolong masukkan kalimat terlebih dahulu.")
else:
# Tokenisasi
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
# Prediksi
with torch.no_grad():
outputs = model(**inputs)
probs = torch.softmax(outputs.logits, dim=1)
pred_tensor = torch.argmax(probs, dim=1)
pred = int(pred_tensor.cpu().numpy()[0])
# Ambil label
label = label_map.get(pred, "Unknown")
st.subheader("Hasil Prediksi:")
st.write("Kelas:", f"**{label}**")
st.write("Probabilitas:", probs.tolist()[0])
|