Upload 11 files

app.py

@@ -0,0 +1,652 @@
+
+# streamlit_app.py
+
+
+# import streamlit as st
+# from streamlit_lottie import st_lottie
+# from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+# import torch
+# import json
+
+# # ---------------- Load Model ----------------
+# @st.cache_resource
+# def load_model():
+#     model_name = "./models"  # path to your fine-tuned model
+#     tokenizer = AutoTokenizer.from_pretrained(model_name)
+#     model = AutoModelForSequenceClassification.from_pretrained(model_name)
+#     classifier = pipeline("text-classification", model=model, tokenizer=tokenizer, return_all_scores=True)
+#     return classifier
+
+# classifier = load_model()
+
+# # ---------------- CSS Styles ----------------
+# st.markdown(
+#     """
+#     <style>
+#     body {
+#         background: linear-gradient(-45deg, #ff4b4b, #ff8c00, #4b7fff, #7d00ff);
+#         animation: gradientBG 15s ease infinite;
+#         height: 100vh;
+#     }
+
+#     @keyframes gradientBG {
+#         0% {background-position: 0% 50%;}
+#         50% {background-position: 100% 50%;}
+#         100% {background-position: 0% 50%;}
+#     }
+
+#     .title {
+#         font-size: 55px;
+#         font-weight: bold;
+#         background: linear-gradient(270deg, 
+#             #ff0000, #ff7f00, #ffff00, #00ff00, 
+#             #0000ff, #4b0082, #8f00ff, #ff0000);
+#         background-size: 1500% 1500%;
+#         -webkit-background-clip: text;
+#         -webkit-text-fill-color: transparent;
+#         animation: rainbow 10s linear infinite;
+#         margin-bottom: 10px;
+#     }
+
+#     @keyframes rainbow {
+#         0% {background-position: 0% 50%;}
+#         50% {background-position: 100% 50%;}
+#         100% {background-position: 0% 50%;}
+#     }
+
+#     .intro-line {
+#         font-size: 18px;
+#         color: white;
+#         margin-bottom: 25px;
+#         font-style:italic;
+#     }
+
+#     .stButton button {
+#         display: block;
+#         margin: 30px auto;
+#         background: linear-gradient(90deg, #ff4b4b, #ff8c00);
+#         color: white;
+#         border-radius: 12px;
+#         height: 3em;
+#         width: 12em;
+#         font-size: 18px;
+#         font-weight: bold;
+#         border: none;
+#         box-shadow: 0px 4px 10px rgba(0,0,0,0.3);
+#         transition: 0.3s;
+#     }
+#     .stButton button:hover {
+#         transform: scale(1.1);
+#         background: linear-gradient(90deg, #7d00ff, #00d4ff);
+#     }
+
+#     .output-box {
+#         padding: 15px;
+#         border-radius: 12px;
+#         margin-top: 20px;
+#         font-size: 20px;
+#         font-weight: bold;
+#         text-align: center;
+#     }
+#     .safe {
+#         background-color: rgba(0,255,0,0.2);
+#         color: #00ff7f;
+#     }
+#     .bully {
+#         background-color: rgba(255,0,0,0.2);
+#         color: #ff4b4b;
+#     }
+#     </style>
+#     """,
+#     unsafe_allow_html=True
+# )
+
+# # ---------------- Load Lottie Animation ----------------
+# with open("Cybersecurity.json", "r") as f:
+#     lottie_anim = json.load(f)
+
+# # ---------------- Layout ----------------
+# col1, col2 = st.columns([2, 1])
+
+# with col1:
+#     st.markdown("<div class='title'>Cyberbullying Detection System</div>", unsafe_allow_html=True)
+#     st.markdown("<div class='intro-line'>This tool analyzes text messages and helps identify possible cyberbullying patterns.</div>", unsafe_allow_html=True)
+
+# with col2:
+#     st_lottie(lottie_anim, height=250, key="cyberbully")
+
+# # ---------------- Input Section ----------------
+# st.markdown("### Enter a message :")
+# user_input = st.text_area("", "")
+
+# # ---------------- Prediction Button ----------------
+# if st.button("🔍 Detect"):
+#     if not user_input.strip():
+#         st.warning("Please enter some text.")
+#     else:
+#         results = classifier(user_input)[0]
+#         best = max(results, key=lambda x: x['score'])
+#         label = best['label']
+#         score = best['score']
+
+#         # Cyberbullying logic
+#         if label.lower() == "not_cyberbullying":
+#             result = f"<div class='output-box safe'>✅ Safe message (Confidence: {score:.2f})</div>"
+#         else:
+#             result = f"<div class='output-box bully'>⚠️ Cyberbullying detected ({label})<br>Confidence: {score:.2f}</div>"
+
+#         st.markdown(result, unsafe_allow_html=True)
+
+#         # Probability dictionary
+#         probs = {r['label']: round(r['score'], 3) for r in results}
+#         st.json(probs)
+
+
+# gradio_app.py
+
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+# ---------------- Load Model ----------------
+def load_model():
+    model_path = "./models"
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(model_path)
+    return pipeline(
+        "text-classification",
+        model=model,
+        tokenizer=tokenizer,
+        return_all_scores=True
+    )
+classifier = load_model()
+# ---------------- Prediction Logic ----------------
+def predict(text):
+    if not text.strip():
+        return "<div class='warn'>⚠️ Please enter some text.</div>"
+    results = classifier(text)[0]
+    best = max(results, key=lambda x: x["score"])
+    label = best["label"]
+    score = best["score"]
+    if label.lower() == "not_cyberbullying":
+        return f"""
+        <div class='safe'>
+            <div class='checkmark'>✅</div>
+            <div class='safe-text'>Safe Message</div>
+            <div class='confidence-bar'>
+                <div class='confidence-fill safe-fill' style='width: {score*100}%'></div>
+            </div>
+            <span class='confidence-score'>Confidence: {score:.2%}</span>
+        </div>
+        """
+    else:
+        return f"""
+        <div class='bully'>
+            <div class='warning-icon'>⚠️</div>
+            <div class='bully-text'>Cyberbullying Detected</div>
+            <div class='label-badge'>{label}</div>
+            <div class='confidence-bar'>
+                <div class='confidence-fill bully-fill' style='width: {score*100}%'></div>
+            </div>
+            <span class='confidence-score'>Confidence: {score:.2%}</span>
+        </div>
+        """
+# ---------------- UI ----------------
+with gr.Blocks(theme=gr.themes.Soft(), css="""
+<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/animate.css/4.1.1/animate.min.css"/>
+
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+}
+
+html, body {
+    background: linear-gradient(-45deg, #ff4b4b, #ff8c00, #4b7fff, #7d00ff);
+    background-size: 400% 400%;
+    animation: gradientBG 15s ease infinite;
+    font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+    min-height: 100vh;
+    position: fixed;
+    width: 100%;
+    height: 100%;
+}
+
+@keyframes gradientBG {
+    0% {background-position: 0% 50%;}
+    25% {background-position: 100% 50%;}
+    50% {background-position: 100% 100%;}
+    75% {background-position: 0% 100%;}
+    100% {background-position: 0% 50%;}
+}
+
+.gradio-container {
+    background: rgba(20, 20, 40, 0.85) !important;
+    border-radius: 25px !important;
+    box-shadow: 0 25px 80px rgba(0, 0, 0, 0.4), inset 0 0 30px rgba(255, 255, 255, 0.1) !important;
+    backdrop-filter: blur(15px) !important;
+    border: 1px solid rgba(255, 255, 255, 0.15) !important;
+    padding: 40px !important;
+}
+
+.title {
+    font-size: 52px;
+    font-weight: 900;
+    text-align: center;
+    background: linear-gradient(135deg, #ff4b4b, #ff8c00, #4b7fff, #7d00ff);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+    background-clip: text;
+    animation: slideInDown 1s ease-out, glow 3s ease-in-out infinite;
+    margin-bottom: 10px;
+    text-shadow: 0 0 30px rgba(255, 75, 75, 0.5);
+}
+
+@keyframes slideInDown {
+    from {
+        opacity: 0;
+        transform: translateY(-50px);
+    }
+    to {
+        opacity: 1;
+        transform: translateY(0);
+    }
+}
+
+@keyframes glow {
+    0%, 100% {
+        text-shadow: 0 0 20px rgba(255, 75, 75, 0.5), 0 0 40px rgba(255, 140, 0, 0.3);
+    }
+    50% {
+        text-shadow: 0 0 30px rgba(75, 127, 255, 0.6), 0 0 60px rgba(125, 0, 255, 0.4);
+    }
+}
+
+.subtitle {
+    text-align: center;
+    color: #e0e0ff;
+    margin-bottom: 30px;
+    font-style: italic;
+    font-size: 16px;
+    animation: fadeInUp 1s ease-out 0.2s both;
+    letter-spacing: 1px;
+}
+
+@keyframes fadeInUp {
+    from {
+        opacity: 0;
+        transform: translateY(30px);
+    }
+    to {
+        opacity: 1;
+        transform: translateY(0);
+    }
+}
+
+/* Input Container */
+.textbox-container {
+    animation: scaleIn 0.7s ease-out 0.3s both;
+}
+
+@keyframes scaleIn {
+    from {
+        opacity: 0;
+        transform: scale(0.9) rotateX(10deg);
+    }
+    to {
+        opacity: 1;
+        transform: scale(1) rotateX(0deg);
+    }
+}
+
+textarea {
+    background: rgba(255, 255, 255, 0.08) !important;
+    border: 2px solid rgba(75, 127, 255, 0.3) !important;
+    border-radius: 15px !important;
+    padding: 18px !important;
+    font-size: 16px !important;
+    color: #e0e0ff !important;
+    transition: all 0.4s cubic-bezier(0.34, 1.56, 0.64, 1) !important;
+    box-shadow: 0 8px 32px rgba(75, 127, 255, 0.1), inset 0 0 20px rgba(255, 255, 255, 0.05) !important;
+    backdrop-filter: blur(10px) !important;
+}
+
+textarea::placeholder {
+    color: rgba(224, 224, 255, 0.5) !important;
+}
+
+textarea:focus {
+    border-color: #4b7fff !important;
+    box-shadow: 0 15px 50px rgba(75, 127, 255, 0.4), inset 0 0 30px rgba(75, 127, 255, 0.1) !important;
+    transform: translateY(-5px) scale(1.02);
+    animation: inputGlow 2s ease-in-out infinite;
+}
+
+@keyframes inputGlow {
+    0%, 100% {
+        box-shadow: 0 15px 50px rgba(75, 127, 255, 0.4), inset 0 0 30px rgba(75, 127, 255, 0.1);
+    }
+    50% {
+        box-shadow: 0 20px 60px rgba(125, 0, 255, 0.5), inset 0 0 40px rgba(125, 0, 255, 0.2);
+    }
+}
+
+/* Button Styling with Ripple Effect */
+.btn-primary {
+    background: linear-gradient(135deg, #4b7fff, #7d00ff, #ff4b4b) !important;
+    background-size: 300% 300% !important;
+    border: 2px solid rgba(75, 127, 255, 0.5) !important;
+    color: white !important;
+    font-weight: 700 !important;
+    font-size: 16px !important;
+    padding: 14px 40px !important;
+    border-radius: 50px !important;
+    cursor: pointer !important;
+    transition: all 0.4s ease !important;
+    box-shadow: 0 10px 40px rgba(75, 127, 255, 0.4), inset 0 0 20px rgba(255, 255, 255, 0.1) !important;
+    animation: bounceIn 0.8s cubic-bezier(0.68, -0.55, 0.265, 1.55) 0.4s both;
+    position: relative;
+    overflow: hidden;
+}
+
+@keyframes bounceIn {
+    0% {
+        opacity: 0;
+        transform: scale(0.1) rotateZ(-45deg);
+    }
+    50% {
+        opacity: 1;
+        transform: scale(1.1) rotateZ(10deg);
+    }
+    100% {
+        transform: scale(1) rotateZ(0deg);
+    }
+}
+
+.btn-primary:hover {
+    transform: translateY(-5px) scale(1.05);
+    box-shadow: 0 20px 60px rgba(125, 0, 255, 0.6), inset 0 0 30px rgba(255, 255, 255, 0.15) !important;
+    background-position: 100% 0 !important;
+    animation: gradientShift 3s ease infinite;
+}
+
+@keyframes gradientShift {
+    0% {background-position: 0% 50%;}
+    50% {background-position: 100% 50%;}
+    100% {background-position: 0% 50%;}
+}
+
+.btn-primary:active {
+    transform: translateY(-2px) scale(0.98);
+}
+
+/* Ripple Effect */
+.btn-primary::before {
+    content: '';
+    position: absolute;
+    top: 50%;
+    left: 50%;
+    width: 0;
+    height: 0;
+    border-radius: 50%;
+    background: rgba(255, 255, 255, 0.6);
+    transform: translate(-50%, -50%);
+    transition: width 0.6s, height 0.6s;
+}
+
+.btn-primary:active::before {
+    width: 400px;
+    height: 400px;
+}
+
+/* Result Cards */
+.safe {
+    background: linear-gradient(135deg, rgba(0, 255, 100, 0.15), rgba(100, 255, 150, 0.08));
+    border: 2px solid rgba(0, 255, 100, 0.4);
+    padding: 35px;
+    border-radius: 20px;
+    color: #00ff64;
+    text-align: center;
+    animation: slideInRight 0.8s cubic-bezier(0.34, 1.56, 0.64, 1), cardGlowGreen 3s ease-in-out infinite;
+    box-shadow: 0 20px 60px rgba(0, 255, 100, 0.25), inset 0 0 30px rgba(0, 255, 100, 0.1);
+    backdrop-filter: blur(15px);
+}
+
+.bully {
+    background: linear-gradient(135deg, rgba(255, 0, 0, 0.15), rgba(255, 100, 100, 0.08));
+    border: 2px solid rgba(255, 107, 107, 0.4);
+    padding: 35px;
+    border-radius: 20px;
+    color: #ff6b6b;
+    text-align: center;
+    animation: slideInRight 0.8s cubic-bezier(0.34, 1.56, 0.64, 1), cardGlowRed 2s ease-in-out infinite;
+    box-shadow: 0 20px 60px rgba(255, 107, 107, 0.25), inset 0 0 30px rgba(255, 107, 107, 0.1);
+    backdrop-filter: blur(15px);
+}
+
+@keyframes slideInRight {
+    from {
+        opacity: 0;
+        transform: translateX(100px) rotateY(20deg);
+    }
+    to {
+        opacity: 1;
+        transform: translateX(0) rotateY(0deg);
+    }
+}
+
+@keyframes cardGlowGreen {
+    0%, 100% {
+        box-shadow: 0 20px 60px rgba(0, 255, 100, 0.25), inset 0 0 30px rgba(0, 255, 100, 0.1);
+    }
+    50% {
+        box-shadow: 0 30px 80px rgba(0, 255, 100, 0.4), inset 0 0 40px rgba(0, 255, 100, 0.2);
+    }
+}
+
+@keyframes cardGlowRed {
+    0%, 100% {
+        box-shadow: 0 20px 60px rgba(255, 107, 107, 0.25), inset 0 0 30px rgba(255, 107, 107, 0.1);
+    }
+    50% {
+        box-shadow: 0 30px 80px rgba(255, 107, 107, 0.4), inset 0 0 40px rgba(255, 107, 107, 0.2);
+    }
+}
+
+.warn {
+    color: #ffb700;
+    text-align: center;
+    font-weight: 700;
+    font-size: 18px;
+    animation: shake 0.5s ease-in-out, pulse 1.5s ease-in-out infinite 0.5s;
+    padding: 20px;
+}
+
+@keyframes shake {
+    0%, 100% {transform: translateX(0);}
+    10%, 30%, 50%, 70%, 90% {transform: translateX(-8px);}
+    20%, 40%, 60%, 80% {transform: translateX(8px);}
+}
+
+@keyframes pulse {
+    0%, 100% {opacity: 1;}
+    50% {opacity: 0.6;}
+}
+
+/* Icons */
+.checkmark, .warning-icon {
+    font-size: 56px;
+    margin-bottom: 15px;
+    animation: bounce 0.8s cubic-bezier(0.68, -0.55, 0.265, 1.55);
+    display: inline-block;
+}
+
+@keyframes bounce {
+    0% {
+        opacity: 0;
+        transform: scale(0) rotateZ(-45deg);
+    }
+    50% {
+        transform: scale(1.2) rotateZ(15deg);
+    }
+    100% {
+        opacity: 1;
+        transform: scale(1) rotateZ(0deg);
+    }
+}
+
+.warning-icon {
+    animation: bounce 0.8s cubic-bezier(0.68, -0.55, 0.265, 1.55), pulse-warning 1.5s ease-in-out 0.8s infinite;
+}
+
+@keyframes pulse-warning {
+    0%, 100% {
+        transform: scale(1);
+        filter: drop-shadow(0 0 5px rgba(255, 107, 107, 0.5));
+    }
+    50% {
+        transform: scale(1.2);
+        filter: drop-shadow(0 0 20px rgba(255, 107, 107, 1));
+    }
+}
+
+/* Text */
+.safe-text, .bully-text {
+    font-size: 28px;
+    font-weight: 800;
+    margin-bottom: 15px;
+    animation: fadeInDown 0.8s ease-out 0.2s both;
+    letter-spacing: 0.5px;
+}
+
+@keyframes fadeInDown {
+    from {
+        opacity: 0;
+        transform: translateY(-20px);
+    }
+    to {
+        opacity: 1;
+        transform: translateY(0);
+    }
+}
+
+.label-badge {
+    display: inline-block;
+    background: rgba(255, 107, 107, 0.2);
+    border: 2px solid rgba(255, 107, 107, 0.5);
+    padding: 10px 20px;
+    border-radius: 25px;
+    margin-bottom: 18px;
+    font-size: 14px;
+    font-weight: 700;
+    animation: zoomIn 0.7s ease-out 0.3s both;
+    box-shadow: 0 5px 20px rgba(255, 107, 107, 0.2);
+}
+
+@keyframes zoomIn {
+    from {
+        opacity: 0;
+        transform: scale(0.3);
+    }
+    to {
+        opacity: 1;
+        transform: scale(1);
+    }
+}
+
+/* Confidence Bar */
+.confidence-bar {
+    width: 100%;
+    height: 10px;
+    background: rgba(255, 255, 255, 0.1);
+    border-radius: 12px;
+    margin-bottom: 15px;
+    overflow: hidden;
+    animation: fadeIn 0.8s ease-out 0.1s both;
+    border: 1px solid rgba(255, 255, 255, 0.2);
+    box-shadow: inset 0 0 10px rgba(0, 0, 0, 0.3);
+}
+
+.confidence-fill {
+    height: 100%;
+    border-radius: 12px;
+    transition: width 1.2s cubic-bezier(0.34, 1.56, 0.64, 1);
+    animation: fillWidth 1.2s ease-out;
+}
+
+@keyframes fillWidth {
+    from {
+        width: 0 !important;
+    }
+}
+
+.safe-fill {
+    background: linear-gradient(90deg, #00ff64, #00d452, #00ff64);
+    background-size: 200% 200%;
+    box-shadow: 0 0 25px rgba(0, 255, 100, 0.8), inset 0 0 10px rgba(255, 255, 255, 0.3);
+    animation: fillWidth 1.2s ease-out, shimmer 2s ease-in-out infinite;
+}
+
+.bully-fill {
+    background: linear-gradient(90deg, #ff6b6b, #ff4444, #ff6b6b);
+    background-size: 200% 200%;
+    box-shadow: 0 0 25px rgba(255, 107, 107, 0.8), inset 0 0 10px rgba(255, 255, 255, 0.3);
+    animation: fillWidth 1.2s ease-out, shimmer 2s ease-in-out infinite;
+}
+
+@keyframes shimmer {
+    0%, 100% {background-position: 0% 50%;}
+    50% {background-position: 100% 50%;}
+}
+
+.confidence-score {
+    font-size: 15px;
+    opacity: 0.9;
+    animation: fadeIn 0.8s ease-out 0.4s both;
+    font-weight: 600;
+    letter-spacing: 0.5px;
+}
+
+@keyframes fadeIn {
+    from {
+        opacity: 0;
+    }
+    to {
+        opacity: 1;
+    }
+}
+
+/* Responsive */
+@media (max-width: 768px) {
+    .title {
+        font-size: 36px;
+    }
+    
+    .safe, .bully {
+        padding: 25px;
+    }
+    
+    html, body {
+        background-size: 600% 600%;
+    }
+}
+""") as demo:
+    gr.Markdown("<div class='title'>🛡️ Cyberbullying Detection System</div>")
+    gr.Markdown("<div class='subtitle'>End-to-end NLP system for detecting cyberbullying, including religion-based abuse</div>")
+    
+    with gr.Group():
+        text_input = gr.Textbox(
+            lines=4,
+            placeholder="Enter a message to analyze...",
+            label="Input Text",
+            elem_classes="textbox-container"
+        )
+        detect_btn = gr.Button("🔍 Detect", variant="primary")
+    
+    output = gr.HTML()
+    
+    detect_btn.click(
+        fn=predict,
+        inputs=text_input,
+        outputs=output
+    )
+
+demo.launch()

config.json

@@ -0,0 +1,40 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "age",
+    "1": "ethnicity",
+    "2": "gender",
+    "3": "not_cyberbullying",
+    "4": "other_cyberbullying",
+    "5": "religion"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "age": 0,
+    "ethnicity": 1,
+    "gender": 2,
+    "not_cyberbullying": 3,
+    "other_cyberbullying": 4,
+    "religion": 5
+  },
+  "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": "4.53.3",
+  "vocab_size": 30522
+}

label_encoder.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d35a74ab441b00df61647ebadbf784cad8d849a048788bed9b19a3b1fd793f
+size 553

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e641cce650040e4a147564cab82b12e7e8260f7d02ff1410399f171a51403ead
+size 267844872

requirements.txt

@@ -0,0 +1,7 @@
+numpy
+pandas
+scikit-learn
+torch
+transformers
+datasets
+accelerate

special_tokens_map.json

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

tfidf_logreg_best.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796a2bcd126927b9e0aef0bcc3f85bbb5e36fec7af5e499db011524dcc363708
+size 10399084

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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2f784b7e538494e42c73130341a5dab79b4b13041d7e2bcc4e1ced3397ffe0
+size 5304