softfluffyboy
SFBAI
AI & ML interests
LLm, STORY generation,C and C++ code optimization,
Recent Activity
new activity
4 days ago
mradermacher/model_requests:reqest quants multillama-3.2-merge
liked
a model
5 days ago
iangitonga/llama32
updated
a dataset
5 days ago
SFBAI/softfluffyboys_yiffmaster_storywriter
Organizations
None yet
SFBAI's activity
reqest quants multillama-3.2-merge
2
#521 opened 5 days ago
by
SFBAI
request quantize
2
#520 opened 5 days ago
by
SFBAI
Priorities
3
#6 opened 7 days ago
by
hexgrad
Broken Meta-Llama-3.1-8B-Instruct-abliterated
3
#519 opened 7 days ago
by
chibop
Request : huihui-ai/EXAONE-3.5-7.8B-Instruct-abliterated
2
#82 opened 15 days ago
by
SFBAI
request: uncensored version
2
#1 opened 17 days ago
by
SFBAI
Request: huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated
2
#81 opened 17 days ago
by
SFBAI
abliteration request for LG's EXAONE models
2
#1 opened 18 days ago
by
SFBAI
porting code to C++ aka TRELLIS.cpp
#3 opened 21 days ago
by
SFBAI
finetuning help
2
#1 opened 5 months ago
by
SFBAI
uncensored (abliterated) version?
3
#1 opened 3 months ago
by
SFBAI
What is magpie?
2
#2 opened 3 months ago
by
ddh0
data source?
8
#1 opened 5 months ago
by
Fizzarolli
๐ฉ Report: Not working
7
#14 opened 3 months ago
by
frank0071
request: Llama-3.2 abliterated
2
#14 opened 3 months ago
by
SFBAI
feedback
1
#2 opened 5 months ago
by
SFBAI
Recommended hardware?
13
#1 opened 5 months ago
by
sdalemorrey
abliterated version
2
#1 opened 5 months ago
by
SFBAI
[bug] KoboldCpp 1.71.1 wrong detection of quants not only llama type and cause quality loss
2
#1 opened 5 months ago
by
SFBAI
that kind trolling?
6
#1 opened 5 months ago
by
SFBAI