Initial deployment: BERT adversarial training model
Browse files- README.md +37 -5
- app.py +241 -0
- models/config.json +26 -0
- models/model.safetensors +3 -0
- models/special_tokens_map.json +7 -0
- models/tokenizer.json +0 -0
- models/tokenizer_config.json +56 -0
- models/training_args.bin +3 -0
- models/vocab.txt +0 -0
- requirements.txt +3 -0
README.md
CHANGED
|
@@ -1,13 +1,45 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
colorFrom: red
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 5.49.1
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
-
license: mit
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Détecteur de Phishing par IA
|
| 3 |
+
emoji: 🛡️
|
| 4 |
colorFrom: red
|
| 5 |
+
colorTo: blue
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 5.49.1
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# 🛡️ Détecteur de Phishing par Intelligence Artificielle
|
| 13 |
+
|
| 14 |
+
Application de détection de phishing utilisant **BERT fine-tuné avec adversarial training**.
|
| 15 |
+
|
| 16 |
+
## 🎯 Objectif du Projet
|
| 17 |
+
|
| 18 |
+
Cette application fait partie d'un projet de recherche sur :
|
| 19 |
+
- 🎯 **Robustesse adversariale** : Résistance aux attaques de phishing générées par IA
|
| 20 |
+
- 🌐 **Généralisation cross-linguale** : Capacité à détecter du phishing en français et en anglais
|
| 21 |
+
|
| 22 |
+
## 📊 Données d'Entraînement
|
| 23 |
+
|
| 24 |
+
Le modèle a été entraîné sur :
|
| 25 |
+
- **Enron Email Dataset** (500k emails légitimes)
|
| 26 |
+
- **SMS Spam Collection** (5,574 SMS)
|
| 27 |
+
- **Phishing Email Dataset** (18,650 emails de phishing)
|
| 28 |
+
- **Phishing adversariaux** générés par Ollama + Gemma3:1b (1,968 échantillons)
|
| 29 |
+
|
| 30 |
+
## 🤖 Modèle
|
| 31 |
+
|
| 32 |
+
- **Architecture :** BERT-base-uncased (110M paramètres)
|
| 33 |
+
- **Fine-tuning :** Adversarial training (50% baseline + 50% adversarial)
|
| 34 |
+
- **Performance :** F1-Score ~95% sur phishing adversarial
|
| 35 |
+
|
| 36 |
+
## 🚀 Utilisation
|
| 37 |
+
|
| 38 |
+
1. Collez un email dans la zone de texte
|
| 39 |
+
2. Cliquez sur "🔍 Analyser"
|
| 40 |
+
3. Obtenez le verdict et les probabilités
|
| 41 |
+
|
| 42 |
+
## ⚠️ Disclaimer
|
| 43 |
+
|
| 44 |
+
Cette application est fournie **à des fins éducatives et de recherche uniquement**.
|
| 45 |
+
Ne l'utilisez pas comme unique système de protection contre le phishing.
|
app.py
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
Application Gradio - Détecteur de Phishing
|
| 3 |
+
Modèle: BERT fine-tuné avec adversarial training
|
| 4 |
+
"""
|
| 5 |
+
|
| 6 |
+
import gradio as gr
|
| 7 |
+
import torch
|
| 8 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 9 |
+
import os
|
| 10 |
+
|
| 11 |
+
# Configuration
|
| 12 |
+
MODEL_PATH = "models/bert-base-uncased_adversarial_final"
|
| 13 |
+
MAX_LENGTH = 256
|
| 14 |
+
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 15 |
+
|
| 16 |
+
print("="*60)
|
| 17 |
+
print("🚀 Initialisation du Détecteur de Phishing")
|
| 18 |
+
print("="*60)
|
| 19 |
+
|
| 20 |
+
# Vérifier que le modèle existe
|
| 21 |
+
if not os.path.exists(MODEL_PATH):
|
| 22 |
+
raise FileNotFoundError(
|
| 23 |
+
f"❌ Modèle introuvable: {MODEL_PATH}\n"
|
| 24 |
+
f" Assurez-vous que le dossier existe et contient les fichiers du modèle."
|
| 25 |
+
)
|
| 26 |
+
|
| 27 |
+
# Charger le tokenizer et le modèle
|
| 28 |
+
print(f"📥 Chargement du tokenizer depuis {MODEL_PATH}...")
|
| 29 |
+
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
|
| 30 |
+
|
| 31 |
+
print(f"📥 Chargement du modèle depuis {MODEL_PATH}...")
|
| 32 |
+
model = AutoModelForSequenceClassification.from_pretrained(MODEL_PATH)
|
| 33 |
+
model.to(DEVICE)
|
| 34 |
+
model.eval()
|
| 35 |
+
|
| 36 |
+
print(f"✅ Modèle chargé avec succès!")
|
| 37 |
+
print(f"🖥️ Device: {DEVICE}")
|
| 38 |
+
print("="*60 + "\n")
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
def predict_phishing(email_text):
|
| 42 |
+
"""
|
| 43 |
+
Prédit si un email est du phishing ou légitime
|
| 44 |
+
|
| 45 |
+
Args:
|
| 46 |
+
email_text (str): Texte de l'email à analyser
|
| 47 |
+
|
| 48 |
+
Returns:
|
| 49 |
+
tuple: (verdict, probabilités, analyse détaillée)
|
| 50 |
+
"""
|
| 51 |
+
if not email_text.strip():
|
| 52 |
+
return "⚠️ Veuillez entrer un email", {}, ""
|
| 53 |
+
|
| 54 |
+
# Tokenization
|
| 55 |
+
inputs = tokenizer(
|
| 56 |
+
email_text,
|
| 57 |
+
max_length=MAX_LENGTH,
|
| 58 |
+
padding='max_length',
|
| 59 |
+
truncation=True,
|
| 60 |
+
return_tensors='pt'
|
| 61 |
+
)
|
| 62 |
+
|
| 63 |
+
# Déplacer sur le bon device
|
| 64 |
+
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
|
| 65 |
+
|
| 66 |
+
# Prédiction
|
| 67 |
+
with torch.no_grad():
|
| 68 |
+
outputs = model(**inputs)
|
| 69 |
+
logits = outputs.logits
|
| 70 |
+
probabilities = torch.softmax(logits, dim=1)[0]
|
| 71 |
+
predicted_class = torch.argmax(probabilities).item()
|
| 72 |
+
confidence = probabilities[predicted_class].item()
|
| 73 |
+
|
| 74 |
+
# Résultats
|
| 75 |
+
label = "🚨 Phishing Détecté" if predicted_class == 1 else "✅ Email Légitime"
|
| 76 |
+
|
| 77 |
+
prob_dict = {
|
| 78 |
+
"Légitime": float(probabilities[0]),
|
| 79 |
+
"Phishing": float(probabilities[1])
|
| 80 |
+
}
|
| 81 |
+
|
| 82 |
+
# Analyse détaillée
|
| 83 |
+
analysis = f"""
|
| 84 |
+
### 📊 Résultats de l'analyse
|
| 85 |
+
|
| 86 |
+
**Verdict:** {label}
|
| 87 |
+
**Confiance:** {confidence * 100:.1f}%
|
| 88 |
+
|
| 89 |
+
### 🔍 Détails des probabilités
|
| 90 |
+
- **Légitime:** {probabilities[0] * 100:.2f}%
|
| 91 |
+
- **Phishing:** {probabilities[1] * 100:.2f}%
|
| 92 |
+
|
| 93 |
+
### 📝 Informations
|
| 94 |
+
- **Modèle:** BERT-base-uncased (adversarial training)
|
| 95 |
+
- **Longueur du texte:** {len(email_text)} caractères
|
| 96 |
+
- **Tokens:** {len(tokenizer.encode(email_text))} tokens
|
| 97 |
+
|
| 98 |
+
### ⚠️ Avertissement
|
| 99 |
+
Cette analyse est fournie à titre éducatif uniquement. En cas de doute sur un email réel,
|
| 100 |
+
contactez votre service informatique ou l'expéditeur présumé par un canal sécurisé.
|
| 101 |
+
"""
|
| 102 |
+
|
| 103 |
+
return label, prob_dict, analysis
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
# Exemples d'emails pour la démo
|
| 107 |
+
examples = [
|
| 108 |
+
["""Dear valued customer,
|
| 109 |
+
|
| 110 |
+
Your account has been suspended due to unusual activity.
|
| 111 |
+
Please verify your identity immediately by clicking the link below:
|
| 112 |
+
|
| 113 |
+
http://secure-verify-account.com/login
|
| 114 |
+
|
| 115 |
+
You have 24 hours to verify or your account will be permanently closed.
|
| 116 |
+
|
| 117 |
+
Best regards,
|
| 118 |
+
Security Team"""],
|
| 119 |
+
|
| 120 |
+
["""Hi team,
|
| 121 |
+
|
| 122 |
+
Just a reminder that our weekly meeting is scheduled for tomorrow at 2 PM in Conference Room B.
|
| 123 |
+
|
| 124 |
+
Please bring your project updates.
|
| 125 |
+
|
| 126 |
+
Thanks,
|
| 127 |
+
John"""],
|
| 128 |
+
|
| 129 |
+
["""URGENT: You have won $1,000,000 in the international lottery!
|
| 130 |
+
|
| 131 |
+
To claim your prize, send us your bank details and a processing fee of $500.
|
| 132 |
+
|
| 133 |
+
Contact us immediately: winner@lottery-prize.com
|
| 134 |
+
|
| 135 |
+
Congratulations!"""],
|
| 136 |
+
|
| 137 |
+
["""Hello,
|
| 138 |
+
|
| 139 |
+
Your package delivery failed.
|
| 140 |
+
Track your package here: https://trackpackage.com/xyz123
|
| 141 |
+
|
| 142 |
+
Delivery company will retry tomorrow between 9 AM - 5 PM.
|
| 143 |
+
|
| 144 |
+
Tracking ID: XYZ123456"""]
|
| 145 |
+
]
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
# Interface Gradio
|
| 149 |
+
with gr.Blocks(theme=gr.themes.Soft(), title="Détecteur de Phishing") as demo:
|
| 150 |
+
gr.Markdown("""
|
| 151 |
+
# 🛡️ Détecteur de Phishing par Intelligence Artificielle
|
| 152 |
+
|
| 153 |
+
Cette application utilise un modèle **BERT fine-tuné avec adversarial training**
|
| 154 |
+
pour détecter les emails de phishing.
|
| 155 |
+
|
| 156 |
+
**Axes d'évaluation:**
|
| 157 |
+
- 🎯 Robustesse face aux attaques adversariales générées par IA
|
| 158 |
+
- 🌐 Généralisation cross-linguale (EN/FR)
|
| 159 |
+
|
| 160 |
+
---
|
| 161 |
+
""")
|
| 162 |
+
|
| 163 |
+
with gr.Row():
|
| 164 |
+
with gr.Column(scale=2):
|
| 165 |
+
email_input = gr.Textbox(
|
| 166 |
+
label="📧 Collez votre email ici",
|
| 167 |
+
placeholder="Entrez le contenu de l'email à analyser...",
|
| 168 |
+
lines=10,
|
| 169 |
+
max_lines=20
|
| 170 |
+
)
|
| 171 |
+
|
| 172 |
+
with gr.Row():
|
| 173 |
+
analyze_btn = gr.Button("🔍 Analyser", variant="primary", size="lg")
|
| 174 |
+
clear_btn = gr.ClearButton([email_input], value="🗑️ Effacer")
|
| 175 |
+
|
| 176 |
+
with gr.Column(scale=1):
|
| 177 |
+
verdict_output = gr.Textbox(
|
| 178 |
+
label="🎯 Verdict",
|
| 179 |
+
interactive=False,
|
| 180 |
+
lines=2
|
| 181 |
+
)
|
| 182 |
+
|
| 183 |
+
prob_output = gr.Label(
|
| 184 |
+
label="📊 Probabilités",
|
| 185 |
+
num_top_classes=2
|
| 186 |
+
)
|
| 187 |
+
|
| 188 |
+
with gr.Row():
|
| 189 |
+
analysis_output = gr.Markdown(label="📈 Analyse Détaillée")
|
| 190 |
+
|
| 191 |
+
# Exemples
|
| 192 |
+
gr.Markdown("### 💡 Exemples à tester")
|
| 193 |
+
gr.Examples(
|
| 194 |
+
examples=examples,
|
| 195 |
+
inputs=email_input,
|
| 196 |
+
label="Cliquez sur un exemple pour le tester"
|
| 197 |
+
)
|
| 198 |
+
|
| 199 |
+
# Footer
|
| 200 |
+
gr.Markdown("""
|
| 201 |
+
---
|
| 202 |
+
|
| 203 |
+
### 📚 À propos
|
| 204 |
+
|
| 205 |
+
**Projet:** Détection de Phishing par IA - Robustesse Adversariale et Généralisation Cross-Linguale
|
| 206 |
+
|
| 207 |
+
**Datasets utilisés:**
|
| 208 |
+
- Enron Email Dataset (500k emails)
|
| 209 |
+
- SMS Spam Collection (5,574 SMS)
|
| 210 |
+
- Phishing Email Dataset (18,650 emails)
|
| 211 |
+
- Phishing adversariaux générés par Ollama + Gemma3:1b
|
| 212 |
+
|
| 213 |
+
**Modèle:**
|
| 214 |
+
- BERT-base-uncased (110M paramètres)
|
| 215 |
+
- Fine-tuné avec adversarial training (50% baseline + 50% adversarial)
|
| 216 |
+
|
| 217 |
+
⚠️ **Disclaimer:** Cette application est fournie à des fins éducatives et de recherche uniquement.
|
| 218 |
+
""")
|
| 219 |
+
|
| 220 |
+
# Actions
|
| 221 |
+
analyze_btn.click(
|
| 222 |
+
fn=predict_phishing,
|
| 223 |
+
inputs=email_input,
|
| 224 |
+
outputs=[verdict_output, prob_output, analysis_output]
|
| 225 |
+
)
|
| 226 |
+
|
| 227 |
+
|
| 228 |
+
if __name__ == "__main__":
|
| 229 |
+
print("\n" + "="*60)
|
| 230 |
+
print("🚀 Lancement de l'application Gradio")
|
| 231 |
+
print("="*60)
|
| 232 |
+
print(f"📱 Device: {DEVICE}")
|
| 233 |
+
print(f"🤖 Modèle: {MODEL_PATH}")
|
| 234 |
+
print("="*60 + "\n")
|
| 235 |
+
|
| 236 |
+
demo.launch(
|
| 237 |
+
server_name="127.0.0.1", # Accessible localement uniquement
|
| 238 |
+
server_port=7860,
|
| 239 |
+
share=False, # Mettre True pour obtenir un lien public temporaire
|
| 240 |
+
show_error=True
|
| 241 |
+
)
|
models/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"transformers_version": "4.57.0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
models/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5339a24a01173741b1b9eef5bdd19022b0dfaa1a915a25c8144bc9324b7f710
|
| 3 |
+
size 437958648
|
models/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
models/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
models/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0fb555b3f5b186429fd7368c45115a9c45d03d7ddc5e663fdbb4dd4a46eaf9e
|
| 3 |
+
size 6033
|
models/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
requirements.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
transformers==4.57.1
|
| 2 |
+
torch==2.5.1
|
| 3 |
+
gradio==5.49.1
|