Terminal Generative Shell

Natural Language Processing (NLP) and Large Language Models (LLM) with Fine-Tuning LLM and make Chatbot Question answering (QA) with LoRA and Flan-T5 Large

FLUX.1-dev with Qwen2VL Captioner and Prompt Enhancer

Derived from Medical Literature Development: Injecting domain expertise into T5 via precision vocabulary-guided masking. 源自医学文献开发：通过精准词库引导遮蔽，为 T5 注入领域专业知识。医学文献開発に基づく実装：高精度な語彙ガイド付きマスキングにより、T5モデルにドメイン専門知識を注入。(機械翻訳)

[EMNLP/BLP2023] Advancing Bangla Punctuation Restoration by a Monolingual Transformer-Based Method and a Large-Scale Corpus

Text (biz req) to SQL Semantic Parser with LLMs Transfer Learning. This will help Analysts query DB without knowing SQL.

A library for fine-tuning T5-small models to perform information extraction for various NLP tasks.

Píldora formativa sobre SLM (Small Lenguage Model)

Persona Styled Recipes are generated given a list of ingredients

Real-Time Road Incident/Hazard Detection and SMS Alert Notification System using CV models, T5 string generation, and Twilio SMS API.

Abstractive text summarizer built with Streamlit and Hugging Face T5 model to generate concise summaries.

News QA generation and fine tuning an LLM for QA generation (under development)

This project provides code for fine-tuning T5/mT5 models on data preprocessed by T5-Refiner-DomainFocus, enabling improved performance on domain-specific text. 本项目提供针对经过 T5-Refiner-DomainFocus 预处理后的数据进行微调训练的代码，便于在专业领域文本上优化 T5/mT5 模型性能。本プロジェクトは、T5-Refiner-DomainFocus によって前処理されたデータを用いた T5/mT5 モデルのファインチューニング用コードを提供し、専門分野のテキストにおける性能向上を可能にします。（機械翻訳）

Seq2seq transformer from scratch for generative question answering (QA) task.

Code for fine-tuning Google's flan-t5-small model on summarization tasks using the pubmed-abstract-summary dataset

A text summarizer based on google's t5-small model

This repository holds a query engine LLM based on the vector DB of BigBasket products list

Thesis scope: Train and Develop a Table-to-Text Transformer-based model for contextual summarization of tabular data. To achieve this T5-small , T5-base, Bart-base and Llama2 7B chat were finetuned on ToTTo and QTSumm. Regarding ToTTo, the models outperformed the benchmark.

This repository contains the machine learning model used for Textualize, a document summarization application. The model is fine-tuned using the `t5-small` pre-trained model and utilizes the "alexfabbri/multi_news" dataset from Hugging Face for training.