Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
onekqΒ 
posted an update 6 days ago
Post
1738
R1 is still trending. Here is a collection of works trying to replicate R1.
onekq-ai/r1-reproduction-works-67a93f2fb8b21202c9eedf0b

Players include Huggingface (Open R1), Stanford (simple scaling), Berkeley (Bespoke, Open thoughts, etc.), ServiceNow, etc. I know there is another work from HKUST but couldn't find it on πŸ€—. Let me know if I miss any teams.
win10

https://ko-fi.com/post/Sampler-is-all-you-need-NO-train-Y8Y41AIF37
I mainly solve the problem of r1 class model in generation and propose a general sampler method to truly extend the inference time.
Really scaling edge models to a more powerful level.
I'm sorry for promoting my own work under your post.

Β·
onekq

Sure, this is what I intend to do.

But a HF πŸ€— collection cannot include anything outside HF πŸ€—. It has to be a dataset, model, space, or paper. Do you have anything like those?

In this post