Non-engineers guide: Train a LLaMA 2 chatbot

StackLLaMA: A hands-on guide to train LLaMA with RLHF

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signals and ignores rich intrinsic signals lying in model internals. We propose SAERL, a data engineering framework for LLM reinforcement lear...

Code Llama: Llama 2 learns to code

A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake

Introducing the Chatbot Guardrails Arena

Run a Chatgpt-like Chatbot on a Single GPU with ROCm