kaiokendev

kaiokendev's repositories

A prompt/context management system

Language:PythonMIT162 13 4

Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit

Language:PythonMIT61 4 2

Language:PythonMIT700

pages

Language:CSS7 2 1

Just checking this for one sec https://arxiv.org/pdf/2304.11062.pdf

Language:Python3 10

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Language:PythonMIT100

A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.

Language:PythonAGPL-3.0100

Language:Python000

🪺 A simple, clean, customizable Hugo theme

Language:CSSMIT000

MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

Language:PythonMIT000