Our great sponsors
-
impersonator
Chat with an AI simulation of anyone as easily as copy-pasting text into a folder! (by nestordemeure)
-
FlexGen
Discontinued Running large language models like OPT-175B/GPT-3 on a single GPU. Focusing on high-throughput generation. [Moved to: https://github.com/FMInference/FlexGen] (by Ying1123)
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
I do not know if t has been done but one could resuscitate the chatbot's minds by copying the chat history into a GPT based program.
My own impersonator[0] is not designed for that (no persistent chat and a text based interface) but one can already dump the text in a folder and see if the personality if properly reproduced.
[0]: https://github.com/nestordemeure/impersonator
It's really just a gpu vram limitation: affordable GPUs are rather memory starved.
Fortunately people have started writing implementations for pipelining across multiple gpus.
https://github.com/Ying1123/FlexGen