deca-exp/3-ultra-2511
Updated
Cody Cocks
ccocks-deca
AI & ML interests
None yet
Recent Activity
new activity
about 23 hours ago
NobodyExistsOnTheInternet/K3-Q4-GGUF:Insert [your mom so fat] joke here
new activity
2 days ago
NobodyExistsOnTheInternet/K3-Q4-GGUF:Repeat with kimi K2.5?
new activity
about 1 month ago
ArtificialAnalysis/AA-LCR:Percentage point formatting
Organizations
Insert [your mom so fat] joke here
10
#1 opened 5 months ago
by
Jefferderp
Repeat with kimi K2.5?
1
#3 opened 3 days ago
by
nlpguy
Percentage point formatting
2
#8 opened 4 months ago
by
Richy67
Can this run on my Nvidia 1080 ti
👍
🚀
2
4
#9 opened 4 months ago
by
ouchiewouchie
Card forensics using VLM localized prompt approach
2
#11 opened 2 months ago
by
vijayksagi
License cannot be fully viewed without gated access
3
#2 opened 2 months ago
by
WithoutOrdinary
Code for replication?
#1 opened 2 months ago
by
ccocks-deca
updated
a
model
2 months ago
published
a
model
3 months ago
Try coding performance!
#2 opened 3 months ago
by
ccocks-deca
moonshotai/Kimi-K2-Thinking
❤️
35
6
#5985 opened 3 months ago
by
davanstrien
replied to
ZennyKenny's
post
3 months ago
You can use a VLM if you really want an API. That being said, there are a lot of OCR models that can run on CPU (albeit slow)
can anyone tell me how i can use this model for computer use tasks?
1
#1 opened 4 months ago
by
Reality123b
Pending Blog-Explorers Access Request
2
#10 opened 3 months ago
by
KarthikAvinash
Can we do this with less active tokens?
1
#3 opened 4 months ago
by
ccocks-deca
50b per token isn't very efficient... Wonder if we could make this 4: https://huggingface.co/inclusionAI/Ling-1T/blob/main/config.json#L22
is this like the old deca 3?
2
#1 opened 4 months ago
by
JonDoeBeep2
updated
a
model
4 months ago
published
a
model
4 months ago
GGUF WHEN? Where is Bartowski!?
3
#5 opened 4 months ago
by
Hanswalter