Resources

View closed (17)

Llama-3 SillyTavern Presets Sharing

pinned

#5 opened about 1 year ago by

Lewdiculous

Is it normal that Gemma models do not work with kv-cache?

#19 opened 10 months ago by

SolidSnacke

Emphasis DFSM - Nexesenex/kobold.cpp

#18 opened 10 months ago by

Lewdiculous

Question about imatrix

#17 opened 11 months ago by

SolidSnacke

How are you?

#16 opened 11 months ago by

SolidSnacke

[llama.cpp PR#7527] GGUF Quantized KV Support

#15 opened 12 months ago by

Lewdiculous

Abysmal upload speeds right now. Investigation.

#14 opened 12 months ago by

Lewdiculous

Most Scientific RP Model Testing Method (tm) - DoggoEval

#13 opened 12 months ago by

SerialKicked

(GGUF) New Flash Attention Implementation Without Tensor Cores

#11 opened 12 months ago by

Lewdiculous

[solved] The Llama3 and GGUF saga. [transfered-discussion]

#10 opened about 1 year ago by

Lewdiculous

Llama 3 coping mechanisms - Part 4

129

#9 opened about 1 year ago by

Lewdiculous

[llama.cpp PR#6844] Custom Quantizations

#8 opened about 1 year ago by

Virt-io

Quantized Llama-3 koboldcpp/mmproj?

#7 opened about 1 year ago by

Lewdiculous

Llama 3 coping mechanisms - Part 3

#6 opened about 1 year ago by

Lewdiculous

Chaotic alignment - Models

#4 opened about 1 year ago by

Lewdiculous

[commit]

#3 opened about 1 year ago by

Spacellary

Llama 3 coping mechanisms - Part 2

152

#1 opened about 1 year ago by

Lewdiculous