Yibo Zhu
bobzhuyb
AI & ML interests
None yet
Organizations
Will crash EVERY time when the context is >240.000
π€― 1
5
#39 opened 3 months ago
by
Nerdsking
Lower performance of Step-3.5-Flash-Base-Midtrain than Step-3.5-Flash-Base
2
#6 opened 5 months ago
by
monster119120
Question about benchmark results
π₯π 2
8
#5 opened 5 months ago
by
tarruda
Is it possible to release a version with low bit quantization?
4
#11 opened 6 months ago
by
lan0004
Disabling/Reducing model reasoning
5
#22 opened 6 months ago
by
Abdallah1997
Question about Step 3.5 Flash Base model weights release
π 1
3
#21 opened 6 months ago
by
NodeLinker
fp8 version?
1
#15 opened 6 months ago
by
CHNtentes
NVFP4
ππ 6
7
#14 opened 6 months ago
by
reneho
What are the benchmarks of the 4 bit model vs the FP8 model?
2
#9 opened 6 months ago
by
Grossor
NVFP4
ππ 6
7
#14 opened 6 months ago
by
reneho