Add MathArena evaluation result for hmmt/hmmt_feb_2026
#30 opened 12 days ago
by
JasperDekoninck
Transformers v5 compatibility
#29 opened 16 days ago
by
hmellor
I have reasoning datasets for this
#28 opened 17 days ago
by
crownelius
Context Management Reproducibility | 可复现性 ?
👍 1
2
#27 opened 19 days ago
by
pandemo
Add MathArena evaluation result for aime/aime_2026
1
#26 opened 19 days ago
by
JasperDekoninck
Hope to see a 4bits AWQ version
👍 ➕ 10
#25 opened 25 days ago
by
leflak
Question : Real-world use cases for Step-3.5-Flash
8
#24 opened 25 days ago
by
Geodd
Safe trading
1
#23 opened 27 days ago
by
Lyonblaze
Disabling/Reducing model reasoning
5
#22 opened 28 days ago
by
Abdallah1997
Question about Step 3.5 Flash Base model weights release
👍 1
3
#21 opened 29 days ago
by
NodeLinker
update-bmk-numbers
#18 opened 29 days ago
by
mh3467
Deployment of Step-3.5-Flash (fp16) via sglang failed.
➕ 1
7
#17 opened 29 days ago
by
zqzq71
using prompt like this reducing the model reasoning length in my testing
3
#16 opened about 1 month ago
by
gopi87
fp8 version?
1
#15 opened about 1 month ago
by
CHNtentes
NVFP4
🚀 👍 6
7
#14 opened about 1 month ago
by
reneho
Open Network
1
#13 opened about 1 month ago
by
Lawziet
The Soul in the Machine
2
#12 opened about 1 month ago
by
qxet
Add missing task tag!
#11 opened about 1 month ago
by
MihaiPopa-1
BrowseComp with Context Management
➕ 👀 4
#10 opened about 1 month ago
by
yanghao1126
llama.cpp
4
#8 opened about 1 month ago
by
PotatoSniffer
@cerebras please do your thing
🔥 1
2
#6 opened about 1 month ago
by
marksverdhei
Does it support fine-tuning?
#5 opened about 1 month ago
by
taozi555
Recommended sampling parameters?
👍 1
2
#3 opened about 1 month ago
by
sszymczyk
How to use PaCoRe?
5
#2 opened about 1 month ago
by
JJKiks