Remote code: MLA/MTP attention is non-causal for unpadded input under the default (sdpa) load
#15 opened 14 days ago
by
bighead-liat
Docker image - vLLM sm_89
#14 opened 18 days ago
by
juiceb0xc0de
Great model, BUT it loops!
1
#13 opened 22 days ago
by
ZeroWw
Best model for its size, people are not using due to absense of GGUFs.
2
#12 opened 29 days ago
by
Sourajit123
MTP support?
β 14
3
#11 opened about 1 month ago
by
coder543
Supported languages of Ling-3.0 models?
#10 opened about 1 month ago
by
AMAImedia
Great Model
π₯ 4
1
#9 opened about 1 month ago
by
PixelPhilosopher
Excellent, Fast Local Model (somewhat of a review)
β€οΈ 7
9
#4 opened about 2 months ago
by
AMDBartek
Can we get a base model?
ππ 5
3
#3 opened about 2 months ago
by
nraxl1