Understanding materials
#37
by
rishabh-gurbani
- opened
Is there any particular guide that i can follow to get this up and running? i have an 4 x A100 80GB and confused about how to go around, which model to run (the original one/quantised, GPTQ/GGML, AutoGPTQ/Exllama, what's llama.cpp). a guide to understand all these formats would be helpful.