Upload 8 files

🚨 Fake News Detector App

This is a machine learning-powered web app that detects whether a given news article is real or fake.

Built using:

🧠 DistilBERT for natural language understanding

🔥 PyTorch and 🤗 Transformers for model training

🧪 Trained on a labeled dataset of real and fake news articles

🌐 Interactive frontend powered by Streamlit

📥 Input any news content
🎯 Get an instant prediction: Real or Fake

🔐 Works entirely in-browser — no sensitive data stored or shared.

Perfect for:

Fact-checking

Educational demos

NLP beginners exploring transformers

app.py

@@ -0,0 +1,53 @@
+import os
+
+os.environ["STREAMLIT_HOME"] = os.getcwd()
+os.environ["STREAMLIT_BROWSER_GATHER_USAGE_STATS"] = "false"
+
+import streamlit as st
+# rest of your imports and app code...
+
+
+# Redirect Hugging Face cache to /tmp (a writable location in Spaces)
+os.environ["TRANSFORMERS_CACHE"] = "/tmp"
+
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import streamlit as st
+import torch.nn.functional as F
+
+# Set page config FIRST
+st.set_page_config(page_title="📰 Fake News Detector", layout="centered")
+
+# 🚀 Load model and tokenizer
+@st.cache_resource
+def load_model():
+    model = AutoModelForSequenceClassification.from_pretrained("fake-news-model")
+    tokenizer = AutoTokenizer.from_pretrained("fake-news-model")
+    return model, tokenizer
+
+model, tokenizer = load_model()
+model.eval()
+
+# 🎨 Streamlit UI
+st.title("📰 Fake News Detector")
+st.markdown("Enter a news article below to check if it's **Real** or **Fake**.")
+
+text = st.text_area("✍️ Enter news content here:", height=250)
+
+if st.button("🔍 Detect"):
+    if text.strip() == "":
+        st.warning("Please enter some text first.")
+    else:
+        # Tokenize
+        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+        
+        with torch.no_grad():
+            outputs = model(**inputs)
+            logits = outputs.logits
+            probs = F.softmax(logits, dim=1)
+            prediction = torch.argmax(probs, dim=1).item()
+            confidence = probs[0][prediction].item()
+
+        label = "🟢 Real News" if prediction == 1 else "🔴 Fake News"
+        st.subheader(label)
+        st.markdown(f"**Confidence:** {confidence:.2%}")

config.json

@@ -0,0 +1,24 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac056d87db282c4797edeb446c0f7ac27bc7c15bb8cd4a44a76d0d6415a1cb1
+size 267832560

requirements.txt

@@ -1,3 +1,5 @@
-altair
-pandas
-streamlit
+streamlit
+transformers
+torch
+numpy
+pandas

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}