Srikanta K N
srikanta-221
AI & ML interests
None yet
Recent Activity
new activity 10 days ago
google/gemma-4-31B-it:Model seems to have issues in vLLM (characters duplication) new activity 10 days ago
google/gemma-scope-2:Incorrect release name in example for Gemma SAE (-res, not -resid_post) new activity 10 days ago
google/gemma-4-31B-it:124B, pretty please?Organizations
Model seems to have issues in vLLM (characters duplication)
π₯ 1
8
#15 opened 14 days ago
by
dehnhaide
Incorrect release name in example for Gemma SAE (-res, not -resid_post)
1
#2 opened 22 days ago
by
yuhwan
124B, pretty please?
π 25
6
#10 opened 14 days ago
by
vody-am
Gemma 4 MTP
10
#5 opened 14 days ago
by
shadowlilac
please fp8
π 2
1
#4 opened 14 days ago
by
huang123chuan
please fp8
2
#8 opened 14 days ago
by
huang123chuan
Is a QAT fine-tune planned?
ππ₯ 25
1
#14 opened 14 days ago
by
stduhpf
Are you guys going to add other MoE stuff?
π€ 3
2
#11 opened 13 days ago
by
Nesy1
Sentencepiece model file
2
#9 opened 14 days ago
by
Bingsu
Allucination parsing JSON responses containing numerical data such as 1234.00
2
#10 opened 13 days ago
by
jeisonvendetta
Any params/containers to deploy it from HF Inference Endpoints?
π 1
2
#7 opened 15 days ago
by
fabriciocarraro
Missing 'reasoning' field in response when serving gemma-4-31B-it with vLLM
8
#28 opened 12 days ago
by
Iann
Significant Otter! β€
π₯ 3
2
#14 opened 13 days ago
by
MrDevolver
..but where's the bigger one?
π 2
1
#18 opened 13 days ago
by
jerryblunder
Community resources for Gemma 4 deployment β mobile, local, and cloud paths
π 1
2
#6 opened 12 days ago
by
Linncharm
Community resources for Gemma 4 deployment β mobile, local, and cloud paths
1
#27 opened 12 days ago
by
Linncharm
After llama.cpp rework of template parsing, can no longer load this model
π 1
2
#15 opened about 1 month ago
by
quasoft2
How are you handling Gemmaβs license for commercial apps?
2
#122 opened 3 months ago
by
Anonymoose107
Variation of average L0 across layers
3
#3 opened about 2 months ago
by
sjgerstner