Text Generation
Transformers
Safetensors
llama
Generated from Trainer
axolotl
conversational
Inference Endpoints
text-generation-inference

working exlama quants with fixed end token

#1
by Skorcht - opened

when will we get exlama quant? and whats the quality reduction looking like? normally dolphin finetunes are dumber... and will it still adhere to some forms of morals?

ehartford changed discussion status to closed

Sign up or log in to comment