kxshrx/infrnce-bert-classifier

INFRNCE BERT Log Classification Model

This is a fine-tuned DistilBERT model for classifying OpenStack Nova log entries into different operational categories.

Model Details

• Base Model: distilbert-base-uncased
• Task: Multi-class text classification
• Number of Labels: 6
• Domain: OpenStack log analysis

Labels

The model classifies logs into the following categories:

• Error_Handling, - Instance_Management, - Network_Operations, - Resource_Management, - Scheduler_Operations, - System_Operations

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("your-username/infrnce-bert-log-classifier")
model = AutoModelForSequenceClassification.from_pretrained("your-username/infrnce-bert-log-classifier")

# Example usage
log_text = "Your OpenStack log entry here"
inputs = tokenizer(log_text, return_tensors="pt", truncation=True, padding=True, max_length=512)

with torch.no_grad():
    outputs = model(**inputs)
    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
    predicted_class_id = predictions.argmax().item()

print(f"Predicted class: {model.config.id2label[predicted_class_id]}")

Training Data

The model was trained on a curated dataset of OpenStack Nova logs with both regex-based classifications and semantic clustering.

Performance

The model was trained with controlled accuracy to achieve optimal performance on log classification tasks.