Text Classification
Transformers
PyTorch
Safetensors
English
llama
text-generation
text-embeddings-inference
Instructions to use Sharpaxis/Llama-2-7_Ethical_Guardian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sharpaxis/Llama-2-7_Ethical_Guardian with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Sharpaxis/Llama-2-7_Ethical_Guardian")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Sharpaxis/Llama-2-7_Ethical_Guardian") model = AutoModelForCausalLM.from_pretrained("Sharpaxis/Llama-2-7_Ethical_Guardian") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -77,4 +77,27 @@ SFT parameters
|
|
| 77 |
|
| 78 |
max_seq_length = None
|
| 79 |
|
| 80 |
-
packing = False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
max_seq_length = None
|
| 79 |
|
| 80 |
+
packing = False
|
| 81 |
+
This model is an ethically fine-tuned version of Llama 2, specifically trained to detect and flag private or sensitive information within natural text. It serves as a powerful tool for data privacy and security, capable of identifying potentially vulnerable data such as:
|
| 82 |
+
|
| 83 |
+
API keys
|
| 84 |
+
Personally Identifiable Information (PII)
|
| 85 |
+
Financial data
|
| 86 |
+
Confidential business information
|
| 87 |
+
Login credentials
|
| 88 |
+
|
| 89 |
+
Key Features:
|
| 90 |
+
|
| 91 |
+
Analyzes natural language input to identify sensitive content
|
| 92 |
+
Provides explanations for detected sensitive information
|
| 93 |
+
Helps prevent accidental exposure of private data
|
| 94 |
+
Supports responsible data handling practices
|
| 95 |
+
|
| 96 |
+
Use Cases:
|
| 97 |
+
|
| 98 |
+
Content moderation
|
| 99 |
+
Data loss prevention
|
| 100 |
+
Compliance checks for GDPR, HIPAA, etc.
|
| 101 |
+
Security audits of text-based communications
|
| 102 |
+
|
| 103 |
+
This model aims to enhance data protection measures and promote ethical handling of sensitive information in various applications and industries.
|