Lewdiculous
Lewdiculous
AI & ML interests
General lewd and LLM stuff!
https://rentry.co/Lewdiculous
Organizations
Lewdiculous's activity
Llama 3 coping mechanisms - Part 4
125
#9 opened 17 days ago
by
Lewdiculous
(GGUF) New Flash Attention Implementation Without Tensor Cores
19
#11 opened 4 days ago
by
Lewdiculous
Help with convert-hf-to-gguf-update.py
2
#31 opened 3 days ago
by
Zibri
Keep us posted on these experiments.
41
#1 opened 11 days ago
by
Lewdiculous
FA Increases possible context length @Q4
16
#1 opened 6 days ago
by
saishf
My eval tests "command-r" vs "L3-TheSpice-8b-v0.1.3-GGUF-IQ-Imatrix"
5
#2 opened 28 days ago
by
AlekseiPravdin
My experience
8
#2 opened 6 days ago
by
Ardvark123
General discussion.
21
#1 opened 7 days ago
by
Lewdiculous
Llama 3 prompts
33
#1 opened 7 days ago
by
EloyOn
Request: mergekit-community/Synaptica
4
#33 opened 7 days ago
by
ClaudioItaly
General discussion and feedback.
21
#1 opened 13 days ago
by
Lewdiculous
What's different in v2?
1
#1 opened 7 days ago
by
rgbinary
Something isn't working for me.
23
#1 opened 7 days ago
by
Lewdiculous
The Llama3 and GGUF saga continues. [transfered-discussion]
63
#10 opened 10 days ago
by
Lewdiculous
Llama-3 SillyTavern Presets Sharing
38
#5 opened 29 days ago
by
Lewdiculous
GGUF/IMATRIX..?
5
#2 opened 8 days ago
by
rfega4g43qtgeragergr
Feedback
42
#1 opened about 2 months ago
by
Virt-io
GGFU Q8 Please.
7
#1 opened 10 days ago
by
Ransss
Some problems again. They again found some significant error in llama.cpp.
10
#29 opened 13 days ago
by
SolidSnacke
Discussion: Possible upload speed workarounds
3
#32 opened 10 days ago
by
mradermacher
Notice: Requests are paused at the moment.
1
#30 opened 28 days ago
by
Lewdiculous