metadata
license: apache-2.0
language:
- en
library_name: transformers
Model Card: bart_fine_tuned_model
Model Name
generate_summaries
Model Description
This model represents a fine-tuned version of the facebook/bart-large model, specifically adapted for the task of Resume Summarization. The model has been trained to efficiently generate concise and relevant summaries from extensive resume texts. The fine-tuning process has tailored the original BART model to specialize in summarization tasks based on a specific dataset.
Model information
-Base Model: GebeyaTalent/generate_summaries
-Finetuning Dataset: To be made available in the future.
Training Parameters
- Evaluation Strategy: epoch:
- Learning Rate: 5e-5
- Per Device Train Batch Size: 8:
- Per Device Eval Batch Size: 8
- Weight Decay: 0.01
- Save Total Limit: 5
- Number of Training Epochs: 10
- Predict with Generate: True
- Gradient Accumulation Steps: 1
- Optimizer: paged_adamw_32bit
- Learning Rate Scheduler Type: cosine
how to use
1. Install the transformers library:
pip install transformers
2. Import the necessary modules:
import torch
from transformers import BartTokenizer, BartForConditionalGeneration
3. Initialize the model and tokenizer:
model_name = 'GebeyaTalent/generate_summaries'
tokenizer = BartTokenizer.from_pretrained(model_name)
model = BartForConditionalGeneration.from_pretrained(model_name)
4. Prepare the text for summarization:
text = 'Your resume text here'
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding="max_length")
5. Generate the summary:
min_length_threshold = 55
summary_ids = model.generate(inputs["input_ids"], num_beams=4, min_length=min_length_threshold, max_length=150, early_stopping=True)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
6. Output the summary:
print("Summary:", summary)
Model Card Authors
Dereje Hinsermu