Ryan Marten's picture

Ryan Marten

ryanmarten

·

https://ryanmarten.com

AI & ML interests

None yet

Recent Activity

updated a dataset 26 minutes ago

mlfoundations-dev/numina_math_1_5_extra_r1

new activity about 2 hours ago

open-thoughts/OpenThoughts-114k:Appropriate system prompt when finetuning with these traces

updated a model about 2 hours ago

open-thoughts/OpenThinker-7B

View all activity

Organizations

ryanmarten's activity

New activity in open-thoughts/OpenThoughts-114k about 2 hours ago

Appropriate system prompt when finetuning with these traces

#11 opened about 2 hours ago by

New activity in open-thoughts/OpenThoughts-114k about 9 hours ago

Just want to confirm, this is full r1 data?

#3 opened 14 days ago by

Is there a version without special tags?

#10 opened 1 day ago by

New activity in open-thoughts/OpenThoughts-114k 4 days ago

add synthetic tag metadata

#5 opened 13 days ago by

Add synthetic tag

#8 opened 4 days ago by

Update dataset card with visualization of all 114k examples

#9 opened 4 days ago by

New activity in bespokelabs/Bespoke-Stratos-32B 5 days ago

i want to reproduce the result, but encounter some inconsistency with your training curve

#4 opened 6 days ago by

New activity in open-thoughts/OpenThinker-7B 5 days ago

Thank you very much for this model, I have questions

#1 opened 14 days ago by

New activity in bespokelabs/Bespoke-Stratos-32B 12 days ago

What's your benchmark settings for DeepSeek-R1-Distill-Qwen-32B??

#2 opened 13 days ago by

New activity in open-thoughts/OpenThoughts-114k 12 days ago

The meaning of "distillation" - Does it require logit outputs from the teacher model?

#6 opened 12 days ago by

New activity in open-r1/OpenThoughts-114k-math 12 days ago

32,390 wrong math answers?

#3 opened 12 days ago by

Only math

#2 opened 12 days ago by

New activity in bespokelabs/Bespoke-Stratos-32B 19 days ago

fix table

#1 opened 19 days ago by

fix table

#1 opened 19 days ago by