Instruction fine tuning BART for Dialogue Summarization | IT4772E | NLP Project 20232

Flan-t5 model fine tune LoRA and Langchain

Project based on PyTorch-lightning and Transformers for training Seq2SeqLM models, with a primary focus on MT5 and FLAN-T5, yet not limited to them

This repository contains my team's internship project work at Flexbox Technologies. We have developed a system that fills the patient details form automatically with the patient data extracted from pdf file.

This repository contains one of my cool project which I have created during my college's MINeD hack-a-thon.

📣 Forth task on CodSoft Internship During my internship at CodSoft, I had the opportunity to develop a Spam SMS Detection model. The goal was to create a machine-learning solution to classify SMS messages as "ham" or "spam" automatically.

Training and fine-tuning flan-t5-small model based on provided text

Tutorial para treino de um modelo baseado Flan-T5 usando Flax no GCP-TPU

Harness the power of GPT-2 and Flan-T5-Large using a single GPU with LoRA.

The official fork of THoR Chain-of-Thought framework, enhanced and adapted for Emotion Cause Analysis (ECAC-2024)

The codebase for finetuning a flant5 model to include tag in a lyric.

Naive Bayes Model: Cleaned data, engineered features, and achieved impressive results. FLAN-T5 Large Language Model: Explored zero-shot, one-shot, and few-shot inference techniques.

Master's thesis on Large Language Models for Document Visual Question Answering

A preliminary investigation for ontology alignment (OM) with large language models (LLMs).

Document Summarization App using large language model (LLM) and Langchain framework. Used a pre-trained T5 model and its tokenizer from Hugging Face Transformers library. Created a summarization pipeline to generate summary using model.

Symbol Team model for PAN@AP 2023 shared task on Profiling Cryptocurrency Influencers with Few-shot Learning

A gradio frontend for Google's Flan-T5 Large language model, can also be adjusted for other sizes.

Rethinking Negative Instances for Generative Named Entity Recognition

The TABLET benchmark for evaluating instruction learning with LLMs for tabular prediction.

Fine-tuning of Flan-5T LLM for text classification