Update model.yml

model.yml

@@ -13,5 +13,5 @@ stream: true # true | false
 # Engine / Model Settings
 ngl: 33 # 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: "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"