A guidance language for controlling large language models.

Instruct-tune LLaMA on consumer hardware

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

Official inference library for Mistral models

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

links to conference publications in graph-based deep learning

Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the u…

EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction

This repository holds the code for working with data from counselchat.com

Multi-modal Emotion detection from IEMOCAP on Speech, Text, Motion-Capture Data using Neural Nets.

datasets from the paper "Towards Understanding Sycophancy in Language Models"

This repository contains all code and experiments for competitive policy gradient (CoPG) algorithm.

Code for our INTERSPEECH 2022 paper submission titled "Towards Automated Counselling Decision-Making: Remarks on Therapist Action Forecasting on the AnnoMI Dataset"

Code and models for the paper "Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations" at the Web Conference 2021

Speech Emotion Recognition (SER) is an intriguing and dynamic subfield of natural language processing (NLP) and human-computer interaction.