yang
kq
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
Jackrong/Qwopus3.5-27B-v3-GGUF liked a model 5 days ago
QuantTrio/gemma-4-31B-it-AWQ liked a model 5 days ago
QuantTrio/gemma-4-31B-it-AWQ-6BitOrganizations
None yet
This is the best quant version in the world,better than FP8
๐ 5
2
#2 opened about 1 month ago
by
kq
Can we get a 9B-FP8 version next
๐ 14
4
#5 opened about 1 month ago
by
kq
SVG improve needed
#35 opened about 2 months ago
by
kq
how to fix: KeyError: 'model.layers.30.mlp.shared_expert.gate_gate_up_proj.weight'
๐ฅ 1
2
#1 opened 2 months ago
by
kq
How much vram is needed to run this model? 8xRTX3090=192GB isn't enough to run the context.
1
#12 opened 6 months ago
by
kq
FP8/4bit version please
โ 4
5
#7 opened 7 months ago
by
zhanghx0905
AttributeError: 'FusedMoE' object has no attribute 'moe'
2
#1 opened 7 months ago
by
kq
Any idea on how to fix this: KeyError: 'layers.31.mlp.shared_expert.down_proj.weight'
4
#1 opened 7 months ago
by
kq
Multiple function_tool call needed
1
#12 opened 8 months ago
by
kq
so consider build a model for GPU?
3
#1 opened about 1 year ago
by
kq
Supports function calls/structured outputs
4
#2 opened over 1 year ago
by
luijait
I am waiting for your release, just wait here
๐โ 2
3
#1 opened over 1 year ago
by
kq
Supports function calls/structured outputs
4
#2 opened over 1 year ago
by
luijait