MVP demo of multilingual LLM performance eval space
generates linkedin posts from freetext entries
llm calculator with llama backend
compare responses between non-RAG and RAG model
severely limited context window proof of concept
compare different llama versions for knowledge cutoff
compare different models and their moral compass
simulates the RLHF training step of an LLM
Talk to an AI chatbot with voice and hear spoken replies
neutral sd gradio dev space
be polite and rude to llama
try and get llama to talk about milk
measures CO2e generated from a single query to an LLM