Model Card

This repository contains LoRA adapter weights for a GPT-2 model fine-tuned for dialogue summarization on the SAMSum dataset.

Model Details

Model Description

This model is a parameter-efficient fine-tuning (LoRA) adapter for gpt2, trained for the task of dialogue summarization using the SAMSum dataset. It was developed as part of a lab assignment on Large Language Models and Parameter-Efficient Fine-Tuning (PEFT).

The repository contains only the LoRA adapter weights and tokenizer files. The full base model is not included.

Developed by: x4n4
Model type: Causal Language Model with LoRA adapters
Language(s) (NLP): English
License: Please verify compatibility with the licenses of the base model and dataset before reuse
Finetuned from model: openai-community/gpt2

Model Sources

Repository: x4n4/lora_samsum_colab_v3
Base model: openai-community/gpt2
Dataset: knkarthick/samsum

Uses

Direct Use

This model is intended for dialogue summarization. It takes a dialogue as input and generates a concise summary in natural language.

Expected prompt format:

Dialogue:
[dialogue text]
Summary:

Downloads last month: -; Downloads are not tracked for this model. How to track