Less than a megabyte, generates stories but not very coherently!
279 Pulls Updated 5 months ago
Updated 5 months ago
5 months ago
b9231c4268a4 · 750kB
model
archllama
·
parameters656K
·
quantizationQ8_0
749kB
template
{{ .Prompt }}
13B
params
{"stop":["\u003c|end_story|\u003e"]}
37B
Readme
this is a completion/text model, not a chat model. Give it the start of a story and it will complete the rest
This is probably only useful for testing or tiny devices, it generates stories but they aren’t very coherent, imagine a toddler trying to write a story.