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