Search Results for author: Shamane Siriwardhana

Found 8 papers, 6 papers with code

Arcee's MergeKit: A Toolkit for Merging Large Language Models

2 code implementations20 Mar 2024 Charles Goddard, Shamane Siriwardhana, Malikeh Ehghaghi, Luke Meyers, Vlad Karpukhin, Brian Benedict, Mark McQuade, Jacob Solawetz

The rapid expansion of the open-source language model landscape presents an opportunity to merge the competencies of these model checkpoints by combining their parameters.

Language Modelling Multi-Task Learning

Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering

1 code implementation6 Oct 2022 Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Tharindu Kaluarachchi, Rajib Rana, Suranga Nanayakkara

We propose \textit{RAG-end2end}, an extension to RAG, that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training.

Domain Adaptation Information Retrieval +3

Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering

1 code implementation22 Jun 2021 Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Suranga Nanayakkara

In this paper, we illustrate how to fine-tune the entire Retrieval Augment Generation (RAG) architecture in an end-to-end manner.

Open-Domain Question Answering Retrieval

VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation

2 code implementations18 Aug 2019 Shamane Siriwardhana, Rivindu Weerasakera, Denys J. C. Matthies, Suranga Nanayakkara

In this paper, we show how novel transfer reinforcement learning techniques can be applied to the complex task of target driven navigation using the photorealistic AI2THOR simulator.

reinforcement-learning Reinforcement Learning (RL) +2

Universal Successor Features Based Deep Reinforcement Learning for Navigation

no code implementations Master's Thesis - UOA 2019 Shamane Siriwardhana

To cope with the challenges in transfer learning and performance, we present a new approach using Universal Successor Features (USF) in this thesis.

reinforcement-learning Reinforcement Learning (RL) +3

Target Driven Visual Navigation with Hybrid Asynchronous Universal Successor Representations

no code implementations27 Nov 2018 Shamane Siriwardhana, Rivindu Weerasekera, Suranga Nanayakkara

Being able to navigate to a target with minimal supervision and prior knowledge is critical to creating human-like assistive agents.

Navigate Visual Navigation

Cannot find the paper you are looking for? You can Submit a new open access paper.