Llama-3 SillyTavern Presets Sharing
pinned 39
#5 opened about 2 years ago
by 
Lewdiculous
R7B - Unsafe Results
26
#20 opened over 1 year ago
by Lewdiculous
Is it normal that Gemma models do not work with kv-cache?
#19 opened almost 2 years ago
by 
SolidSnacke
Emphasis DFSM - Nexesenex/kobold.cpp
5
#18 opened about 2 years ago
by Lewdiculous
Question about imatrix
6
#17 opened about 2 years ago
by SolidSnacke
How are you?
3
#16 opened about 2 years ago
by SolidSnacke
[llama.cpp PR#7527] GGUF Quantized KV Support
👀 1
22
#15 opened about 2 years ago
by Lewdiculous
Abysmal upload speeds right now. Investigation.
🤗 1
1
#14 opened about 2 years ago
by Lewdiculous
Most Scientific RP Model Testing Method (tm) - DoggoEval
🧠❤️ 3
37
#13 opened about 2 years ago
by 
SerialKicked
(GGUF) New Flash Attention Implementation Without Tensor Cores
22
#11 opened about 2 years ago
by Lewdiculous
[solved] The Llama3 and GGUF saga. [transfered-discussion]
64
#10 opened about 2 years ago
by Lewdiculous
Llama 3 coping mechanisms - Part 4
129
#9 opened about 2 years ago
by Lewdiculous
[llama.cpp PR#6844] Custom Quantizations
6
#8 opened about 2 years ago
by deleted
Quantized Llama-3 koboldcpp/mmproj?
2
#7 opened about 2 years ago
by Lewdiculous
Llama 3 coping mechanisms - Part 3
74
#6 opened about 2 years ago
by Lewdiculous
Chaotic alignment - Models
4
#4 opened about 2 years ago
by Lewdiculous
[commit]
#3 opened about 2 years ago
by 
Spacellary
Llama 3 coping mechanisms - Part 2
❤️ 5
152
#1 opened about 2 years ago
by Lewdiculous