kaiokendev's repositories
cutoff-len-is-context-len
Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit
kaiokendev.github.io
pages
llama-rmt-test
Just checking this for one sec https://arxiv.org/pdf/2304.11062.pdf
text-generation-webui
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
Language:Python000
hugo-paper
🪺 A simple, clean, customizable Hugo theme
Language:CSSMIT000
MeZO
MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
Language:PythonMIT000