Ryan Marten
ryanmarten
AI & ML interests
None yet
Recent Activity
new activity
about 9 hours ago
open-thoughts/OpenThoughts-114k:Thinking templete
updated
a dataset
about 9 hours ago
simplescaling/s1K-claude-3-7-sonnet
updated
a dataset
about 10 hours ago
mlfoundations-dev/s1.2
Organizations
ryanmarten's activity
Thinking templete
2
#15 opened about 12 hours ago
by
fxb
Thinking prompt not included in template
1
#3 opened 4 days ago
by
Doctor-Chad-PhD
Why can't I load the dataset?
3
#12 opened 11 days ago
by
Q20176
STILL-2 subset
1
#9 opened 8 days ago
by
bobox
Training Script?
1
#14 opened 9 days ago
by
justin6667
Librarian Bot: Add language metadata for dataset
#1 opened 10 days ago
by
librarian-bot
Librarian Bot: Add language metadata for dataset
#1 opened 10 days ago
by
librarian-bot
[bot] Conversion to Parquet
#4 opened 28 days ago
by
parquet-converter
Details about training of DeepSeek-R1-Distill-Qwen-7B
1
#5 opened 19 days ago
by
bittersweet
Is it possible to get the full dataset prior to rejection sampling as well
1
#6 opened 12 days ago
by
yeok
Appropriate system prompt when finetuning with these traces
2
#11 opened 14 days ago
by
vgtomahawk
Just want to confirm, this is full r1 data?
9
#3 opened 28 days ago
by
teknium
Is there a version without special tags?
1
#10 opened 15 days ago
by
Kadins
add synthetic tag metadata
1
#5 opened 27 days ago
by
davanstrien
Add synthetic tag
#8 opened 18 days ago
by
davanstrien
Update dataset card with visualization of all 114k examples
1
#9 opened 18 days ago
by
RCL
i want to reproduce the result, but encounter some inconsistency with your training curve
1
#4 opened 19 days ago
by
sqatwork
Thank you very much for this model, I have questions
4
#1 opened 28 days ago
by
NickyNicky
What's your benchmark settings for DeepSeek-R1-Distill-Qwen-32B??
2
#2 opened 26 days ago
by
AaronFeng753