CJ Pais
cjpais
AI & ML interests
realtime ai inference, intentional computing, personal ai, quantization, democratized ml, decentralization
Recent Activity
liked
a model
26 days ago
Zyphra/Zonos-v0.1-hybrid
liked
a model
26 days ago
ZhengPeng7/BiRefNet
liked
a model
26 days ago
briaai/RMBG-2.0
Organizations
cjpais's activity
the model always responses with same answer with different image
1
#9 opened 3 months ago
by
Abdrabu
Error Loading Model
1
#8 opened 6 months ago
by
danielelongo
Large v3 gets stuck
4
#5 opened 6 months ago
by
Ne0nd0g
How to convert the llava to gguf format
1
#7 opened 8 months ago
by
Wangderful
Download just weights to get around Windows limit
3
#2 opened 9 months ago
by
Uneveris
llava_eval_image_embed : failed to eval
5
#6 opened 12 months ago
by
jartine

how to set a proper prompt
1
#6 opened 12 months ago
by
asdf1222
Specify right model card metadata
#1 opened about 1 year ago
by
osanseviero

Specify right model card metadata
#5 opened about 1 year ago
by
osanseviero

Create model card with metadata
#1 opened about 1 year ago
by
osanseviero

Specify right model card metadata
#5 opened about 1 year ago
by
osanseviero

Some things that struck me as odd.
2
#4 opened about 1 year ago
by
DataSoul

update with newly merged llava 1.6 llamacpp support?
4
#3 opened about 1 year ago
by
fuharajugara
Conversion of MoE version of 1.6
2
#2 opened about 1 year ago
by
Jack-771a
Q6_K and Q8_0?
2
#1 opened about 1 year ago
by
xxx777xxxASD

thanks a lot
6
#2 opened about 1 year ago
by
jacek2024
how did you quantize it ?
1
#1 opened about 1 year ago
by
xydac