Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization.

Introduction

DialogLED is a pre-trained model for long dialogue understanding and summarization. It builds on the Longformer-Encoder-Decoder (LED) architecture and uses window-based denoising as the pre-training task on a large amount of long dialogue data for further training. Here is a base version of DialogLED, the input length is limited to 16,384 in the pre-training phase.

Finetuning for Downstream Tasks

Please refer to our GitHub page.

Downloads last month
18
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MingZhong/DialogLED-base-16384

Finetunes
13 models