Code for my thesis titled "Eliciting latent knowledge from language reward models" for the MPhil in Machine Learning and Machine Intelligence at the University of Cambridge
-
Updated
Oct 5, 2023 - Jupyter Notebook
Code for my thesis titled "Eliciting latent knowledge from language reward models" for the MPhil in Machine Learning and Machine Intelligence at the University of Cambridge
This project is based on fine-tuning LLM models (FLAN-T5) for text summarisation task using PEFT approach. All evaluation metrics being computed on ROUGE scoring and LoRA optimisation techniques being used for fine-tuning.
An alternative RLHF reward model formulation from a social choice perspective
RAG Law systems base on google search and Gemini Pro
This repository is dedicated to small projects and some theoretical material that I used to get into NLP and LLM in a practical and efficient way.
Projects and Models built in Python leveraging PyTorch, implementing Reinforcement Learning algorithms for reward-based tasks.
Library built on TextRL for easy training and usage of fine-tuned models using RLHF, a rewards model, and PPO
Applying quantum computing principles to large language models for more reliable, interpretable, and steerable systems.
Survey of preference alignment algorithms
Intelligent AI Chatbot that has the capability to learn from the user
Applying AlphaZero Self-Play Tactics to LLaMA for Enhanced Chatbot Interaction
Direct Preference Optimization of ChatGPT2 using TRL Library
Codebase and experiments of LLM(Large Language Modeling)
Summaries of papers related to the alignment problem in NLP
This repository was commited under the action of executing important tasks on which modern Generative AI concepts are laid on. In particular, we focussed on three coding actions of Large Language Models. Extra and necessary details are given in the README.md file.
Researching the reinforcement learning algorithm of ChatGPT
Embark on the "Reinforcement Learning from Human Feedback" course and align Large Language Models (LLMs) with human values.
Large Language Model for Competitive Programming
Add a description, image, and links to the rlhf topic page so that developers can more easily learn about it.
To associate your repository with the rlhf topic, visit your repo's landing page and select "manage topics."