EsKa
SerialKicked
AI & ML interests
Game development (simplifying quest, image, and story prototyping through neural nets)
Organizations
SerialKicked's activity
Please consider changing the instruct format!
9
#10 opened 2 days ago
by
MarinaraSpaghetti
Any chance you can start providing quants for 24GB cards?
15
#1 opened about 2 months ago
by
RazielAU
GGUF for its little brother?
1
#1 opened about 2 months ago
by
SerialKicked
Feedback
4
#5 opened about 2 months ago
by
SerialKicked
New activity in
LWDCLS/DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-GGUF-IQ-Imatrix-Request
about 2 months ago
100s of download and no one can provide any reviews?
5
#1 opened about 2 months ago
by
dollarpound
System Prompt added to last message
18
#47 opened about 2 months ago
by
turentado
LLM coping mechanisms - Part 5
145
#12 opened 4 months ago
by
Lewdiculous
Hardcoded not to allow 16K context?
#2 opened 3 months ago
by
SerialKicked
Rules and Requests [Status: Accepting Requests]
6
#2 opened 4 months ago
by
SerialKicked
We are so back
5
#3 opened 4 months ago
by
nanowell
Thank you! - Feedback Needed!
20
#1 opened 4 months ago
by
Hastagaras
Keep us posted on these experiments.
55
#1 opened 4 months ago
by
Lewdiculous
One of the worst model for roleplay. Don't even try...
1
#6 opened 4 months ago
by
Musigreg
crashes KoboldCPP 1.66.1
2
#1 opened 4 months ago
by
SerialKicked
[DoggoEval] Test Results
14
#1 opened 4 months ago
by
SerialKicked
Most Scientific RP Model Testing Method (tm) - DoggoEval
37
#13 opened 4 months ago
by
SerialKicked
Feedback / ChatML format issues.
4
#1 opened 4 months ago
by
SerialKicked
Feedback - 02
28
#5 opened 4 months ago
by
Virt-io
Best model i've tried (sometimes?)
7
#1 opened 4 months ago
by
saishf
What is wrong with this AI
3
#9 opened 4 months ago
by
shubka
Llama 3 coping mechanisms - Part 4
129
#9 opened 5 months ago
by
Lewdiculous
Faulty GGUF
#1 opened 4 months ago
by
SerialKicked
Error in 1.7 files
6
#3 opened 5 months ago
by
SerialKicked
How to join the Q6 files?
11
#2 opened 5 months ago
by
AIGUYCONTENT
Incomplete Output even with max_new_tokens
12
#107 opened 9 months ago
by
Pradeep1995
Coherence at 16K
1
#2 opened 5 months ago
by
SerialKicked
Impressive model but.
13
#3 opened 5 months ago
by
SerialKicked
ChatML prompt format problems
3
#7 opened 12 months ago
by
kalomaze