Quick start
from ctransformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("npvinHnivqn/GGUF-metamath-llemma",
model_file="metamath-llemma.gguf",
model_type="llama", gpu_layers=0,
context_length=768)
model('''AI will ''', temperature=0.1)