Intelligent Mixture-of-Models Router for Efficient LLM Inference

한국어 뉴스의 긍정, 부정이 레이블링 된 금융 뉴스 문장 감성 분석 데이터셋 (finance sentiment corpus) 입니다.

LLM Semantic Router: Intelligent Mixture-of-Models (MoM) System with Privacy Preservation and Prompt Guard. The semantic router intelligently directs OpenAI compliant API requests to the most suitable backend models based on semantic understanding of request content.

A server code for serving BERT-based models for text classification. It is designed by SerpApi for heavy-load prototyping and production tasks, specifically for the implementation of the google-local-results-ai-parser gem.

Multi-label classification using LLMs, with additional enhancements using quantization and LoRA (Low-Rank Adaptation). Get better performance on GPU.

Code repository for 2020 Fall COMP4901K Group Project: COVID-19 Named Entity Recognition

Bert Classification on Jigsaw Data with Gender as a basic genre, followed by identifying Bias in Toxic Classification.

In this project, we attempted to analyze users' sentiments on Twitter. For this purpose, we utilized the parsBERT model

bert tasks implementation with huggingface-transformers

Fine-tuning BERT model for text classification with TensorFlow and TensorFlow Hub

Text classification on news articles with BERT.

This project demonstrates twitter sentiment analysis using the BERT model into 3 classes - positive, negative and neutral.

Copy of Repository: https://github.com/Gopu2001/Job-Reaper

Interpseech 2024 - News Topic classification (dataset, evaluation and models source)

(intership) NLP

Large Language Model performing a binary classification task of detecting whether a sarcastic sentence was by a Human or an AI