Model Card for Model ID

This is a finetuned model to summarize logs of any software.

Model Details

BART is a transformer encoder-decoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.

BART is particularly effective when fine-tuned for text generation (e.g. summarization, translation) but also works well for comprehension tasks (e.g. text classification, question answering).

Model Description

This is a log summarizer model which helps in abstractive summarization of log statements. It is based on Bart-base model and has been trained on a synthetic database created by using gpt 3.5.

Usage Example

from transformers import pipeline
from transformers import AutoTokenizer, TFAutoModelForSeq2SeqLM

# Load the fine-tuned model and tokenizer
model = TFAutoModelForSeq2SeqLM.from_pretrained('VidhuMathur/bart-log-summarization')
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-base')

# Create a summarization pipeline using the fine-tuned model and tokenizer
model_pipeline = pipeline("summarization", model=model, tokenizer=tokenizer)

# Example log text for summarization
text = "summarize: 2023-11-15T19:39:02.238394189Z stderr F 2023-11-15 19:39:02,237 INFO [__main__] [server.py:32] [trace_id=6011fa67839c66d0d44542ec0f996416 span_id=8aed01d1fe2a3174 resource.service.name=00688f8f-1904-429a-80b9-06b2c92df17d trace_sampled=True] - executed query: SELECT * FROM profiles WHERE id = '1529' , time taken: 0:00:00.000541"

# Generate a summary using the model
summary = model_pipeline(text)

# Print the generated summary
print(summary[0]['summary_text'])