🍳 applied brainfry
btdeviant
btdeviant
·
AI & ML interests
Tryhard. CV, VQA, VLM, LLM, ASR+TTS, Accessibility
Organizations
None yet
Apr 11 chat template causes ~7.5s template rendering overhead per request in llama.cpp
#27 opened 6 months ago
by btdeviant
The model doesn't serve it's purpose.
13
#2 opened over 3 years ago
by 
max-fry
The model doesn't serve it's purpose.
13
#2 opened over 3 years ago
by max-fry
The model doesn't serve it's purpose.
13
#2 opened over 3 years ago
by max-fry