Sharpaxis/Llama-2-7_Ethical_Guardian

Model Information

model_name = "NousResearch/Llama-2-7b-chat-hf"

dataset_name = "synapsecai/synthetic-sensitive-information"

QLoRA parameters

lora_r = 32

lora_alpha = 8

lora_dropout = 0.1

BitsAndBytes parameters

use_4bit = True

bnb4bitcompute_dtype = "float16"

bnb4bitquant_type = "nf4"

usenestedquant = False

Training Arguments parameters

numtrainepochs = 1

fp16 = False

bf16 = False

perdevicetrainbatchsize = 32

perdeviceevalbatchsize = 8

gradientaccumulationsteps = 4

gradient_checkpointing = True

maxgradnorm = 0.3

learning_rate = 2e-4

weight_decay = 0.001

optim = "pagedadamw32bit"

lrschedulertype = "cosine"

max_steps = -1

warmup_ratio = 0.03

groupbylength = True

save_steps = 0

logging_steps = 25

SFT parameters

maxseqlength = None

packing = False 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:

API keys Personally Identifiable Information (PII) Financial data Confidential business information Login credentials

Key Features:

Analyzes natural language input to identify sensitive content Provides explanations for detected sensitive information Helps prevent accidental exposure of private data Supports responsible data handling practices

Use Cases:

Content moderation Data loss prevention Compliance checks for GDPR, HIPAA, etc. Security audits of text-based communications

This model aims to enhance data protection measures and promote ethical handling of sensitive information in various applications and industries.