context_size: 512
f16: true
threads: 11
gpu_layers: 90
name: mixtral
mmap: true
parameters:
  model: mixtral-8x7b-instruct-v0.1.Q2_K.gguf
  temperature: 0.2
  top_k: 40
  top_p: 0.95
  batch: 512
  tfz: 1.0
template:
  chat: mixtral-chat
  completion: mixtral