Kaizhao Liang

kz919

AI & ML interests

Multimodal foundational model

Recent Activity

updated a model 2 days ago
kz919/QwQ-0.5B-Distilled
updated a model 2 days ago
kz919/QwQ-0.5B-Distilled-gguf
View all activity

Organizations

SambaNova Systems's profile picture Ontocord's M*DEL's profile picture Sambanova-Gradio-Hackathon's profile picture

Posts 6

view post
Post
1307
Just for the meme.

But the clear lesson I learnt from building these demos are, the more powerful the underlying base model is, the closer you will get to GPT4o1. CoT is nothing more than simply inducing the latent reasoning capability from the model.

kz919/GPT4-O1-Proximas