Update model.yml

model.yml

@@ -16,5 +16,5 @@ stream: true # true | false
 # Engine / Model Settings
 ngl: 300 # Infer from base config.json -> num_attention_heads
 ctx_len: 4096 # Infer from base config.json -> max_position_embeddings
-engine: cortex.llamacpp
+engine: llama-cpp
 prompt_template: "<start_of_turn>user\n{prompt}<end_of_turn>\n<start_of_turn>model"