iTharindu

aaivu-dialogue-policy-optimization

Dialogue policy optimization in low resource setting

aaivu-task-oriented-conversational-agent

Building a task-oriented conversational agent for low resource setting using RL for dialogue policy optimization and ensembling for Natural Language Understanding

accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

behavioral-analytics

Behavioral analytics through time series analysis. The time series is used to predict the behavioral patterns and outlier detection is done by comparing real patterns with these behavioral patterns

DialogPolicy

Dialog policy optimization for task-oriented conversational agents in low resource setting using Reinforcement learning. The methodology is based on a novel probability based Self-play technique and a novel Reward based sampling technique that prioritizes failed dialogues over successful ones

fare_classification

Code(winning solution) for the fare calssification challenge which is a private competition hosted at kaggle whrere the goal of the competition is to classify fare as correct or not

generalised-quantifiers-model-checking

We investigate how generalised quantifiers affect the behaviour of transformer-based language models employing the textual entailment problem defined in a purely logical sense, namely, model-checking with natural language.

hand-movement-tracking

System to identify and track hand movements in a video stream with a ego centric view point

SchoolSystem-Nexus

Web based system for a school

SinhalaSongSearch

Sinhala song search app created using elasticsearch and by scraping the web

iTharindu/generalised-quantifiers-model-checking

We investigate how generalised quantifiers affect the behaviour of transformer-based language models employing the textual entailment problem defined in a purely logical sense, namely, model-checking with natural language.

iTharindu/aaivu-dialogue-policy-optimization

Dialogue policy optimization in low resource setting

iTharindu/aaivu-task-oriented-conversational-agent

Building a task-oriented conversational agent for low resource setting using RL for dialogue policy optimization and ensembling for Natural Language Understanding

iTharindu/accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

iTharindu/ccg2lambda

Provide Semantic Parsing solutions and Natural Language Inferences for multiple languages following the idea of the syntax-semantics interface.

iTharindu/hand-movement-tracking

System to identify and track hand movements in a video stream with a ego centric view point

iTharindu/Chain-of-ThoughtsPapers

A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".

iTharindu/deep-reinforcement-learning

iTharindu/diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

iTharindu/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

iTharindu/human-right-sllchrm

iTharindu/image-gpt

iTharindu/iTharindu.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

iTharindu/language_fragments

iTharindu/lecture-python-advanced.notebooks

Notebooks that support https://python-advanced.quantecon.org

iTharindu/lecture-python.notebooks

Notebooks for https://python.quantecon.org

iTharindu/LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

iTharindu/MathBlackBox

iTharindu/nl-sat

We probe Transformer-based language models' ability to solve Natural Language Satisfiability problem instances of varying computational complexity

iTharindu/peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

iTharindu/playground-huggingface-learn

iTharindu/rainbow-is-all-you-need

Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow

iTharindu/reasoning-withing-a-structure

Identifying the limits of Transformers in the problem of model-checking with natural language and determine whether they can learn to understand logical semantics of natural language

iTharindu/reinforcement-learning-algorithmns

Implementation of Reinforcement Learning Algorithms using Pytorch. Value-based methods, Policy based methods as well as Actor-critic methods will be implmented

iTharindu/SLLCHRM

iTharindu/stable-diffusion-webui-automatic111

Stable Diffusion web UI

iTharindu/stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

iTharindu/text2log

Character-based seq2seq models (english => predicate logic)

iTharindu/transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

iTharindu/TransQuest

Transformer based translation quality estimation