Is it feasible to combine diffusion models and language models to mimic divergent thinking?

Stability-AI / StableLM

StableLM: Stability AI Language Models

Apache License 2.0

15.83k stars 1.04k forks source link

Is it feasible to combine diffusion models and language models to mimic divergent thinking? #27

Open win10ogod opened 1 year ago

win10ogod commented 1 year ago

Does using a diffusion model in a language model increase the generality of the language model?

Ph0rk0z commented 1 year ago

well there is stuff like this:

https://github.com/haotian-liu/LLaVA

https://github.com/Vision-CAIR/MiniGPT-4

win10ogod commented 1 year ago

The goal of diffusion models is to learn the latent structure of a dataset by modeling the way in which data points diffuse through the latent space. When used in text generation, it means learning language structure and semantics. I think it should be able to be used in text generation. But I'm not an industry person, just a hobbyist.