Talkie: a 13B vintage language model from 1930
talkie-lm.com
Talkie: a 13B vintage language model from 1930
1–10 of 350 posts
Re: Talkie: a 13B vintage language model from 1930
#2Darn I've only got ~20 GB of VRAM. I really need to get a stronger machine for this sort of stuff.
Re: Talkie: a 13B vintage language model from 1930
#3This is cool. Is it possible to easily install with ollama?
Re: Talkie: a 13B vintage language model from 1930
#4I think that one could also take a much larger model (35B or 122B sized) and give it a thorough system prompt to only speak in the manner of a well educated Victorian/Edwardian era gentleman, if you want an "old timey" LLM.
Re: Talkie: a 13B vintage language model from 1930
#5Vintage is a funny thing to call this. Is it running on vacuum tube hardware?
Re: Talkie: a 13B vintage language model from 1930
#6I think that one could also take a much larger model (35B or 122B sized) and give it a thorough system prompt to only speak in the manner of a well educated Victorian/Edwardian era gentleman, if you want an "old timey" LLM.
As we learn how to train smarter models on less data, it’ll become more and more interesting to see whether models like this can invent post-1930 math, science, etc. and make predictions.
[Edit: serves me right for not reading tfa. My points are well-covered]
Re: Talkie: a 13B vintage language model from 1930
#7>Have you ever daydreamed about talking to someone from the past?
Fun facts, LLM was once envisioned by Steve Jobs in one of his interviews [1].
Essentially one of his main wish in life is to meet and interract with Aristotle, in which according to him at the time, computer in the future can make it possible.
[1] In 1985 Steve Jobs described a machine that would help people get answers from Aristotle–modern LLM [video]:
Re: Talkie: a 13B vintage language model from 1930
#8The Python example is fascinating, and a good rejoinder to anyone still dismissing LLM’s as stochastic parrots.
Re: Talkie: a 13B vintage language model from 1930
#9It is cool. I find the idea of trying to understand whether these types of models can come up with things like General relativity, or maybe some results really interesting.
Re: Talkie: a 13B vintage language model from 1930
#10Darn I've only got ~20 GB of VRAM. I really need to get a stronger machine for this sort of stuff.
How much system memory do you have? Llama.cpp can split layers across cpu and gpu. Speeds will be slower of course but it's not unusable at all.