Article
Accelerating Language Model Inference with Mixture of Attentions
By
•
•
24FilipV
PheelaV
·
AI & ML interests
SW&DS&AI
Recent Activity
upvoted
an
article
17 days ago
Accelerating Language Model Inference with Mixture of Attentions
upvoted
an
article
20 days ago
Deriving DPO's Loss
liked
a Space
5 months ago
HuggingFaceFW/blogpost-fineweb-v1
Organizations
None yet
PheelaV's activity
upvoted
an
article
17 days ago
upvoted
an
article
20 days ago
Article
Deriving DPO's Loss
By
•
•
26
liked
a
Space
5 months ago
Brilliant stuff. Personally I would love to see the discretization and latest A initialization digested. Looking forward to the upcoming posts!
upvoted
an
article
10 months ago
Article
Introduction to State Space Models (SSM)
By
•
•
104
reacted to
lbourdois's
post with ❤️
10 months ago
Post
3577
I stopped procrastinating and finally took the time to write the second article of my series of blog posts on SSM: https://huggingface.co/blog/lbourdois/ssm-2022.
In this blog post, I review the history of SSM models released in 2022, with over 14 models discussed in a synthetic format.
They are separated into two parts: "theoretical" (DSS, S4D, GSS, Mega, S5, etc.) and "applications" (Sashimi, ViS4mer, CCNN, etc.).
To understand everything, it's best to have read the introduction to S4 to SSM blog post first: https://huggingface.co/blog/lbourdois/get-on-the-ssm-train.
All the articles in the series are listed in this space: lbourdois/SSM_blog_posts
Wishing you a good reading :)
In this blog post, I review the history of SSM models released in 2022, with over 14 models discussed in a synthetic format.
They are separated into two parts: "theoretical" (DSS, S4D, GSS, Mega, S5, etc.) and "applications" (Sashimi, ViS4mer, CCNN, etc.).
To understand everything, it's best to have read the introduction to S4 to SSM blog post first: https://huggingface.co/blog/lbourdois/get-on-the-ssm-train.
All the articles in the series are listed in this space: lbourdois/SSM_blog_posts
Wishing you a good reading :)
-
- 2 replies
2.8b model is that the Pile or SlimPJ trained one?