Update model.yml

model.yml

@@ -7,10 +7,10 @@ top_p: 0.95
 temperature: 0.7
 frequency_penalty: 0
 presence_penalty: 0
-max_tokens: 128000 # Infer from base config.json -> max_position_embeddings
+max_tokens: 8192 # Infer from base config.json -> max_position_embeddings
 stream: true # true | false
 stop: ["<|end|>"]
 
 # Engine / Model Settings
-engine: cortex.llamacpp
+engine: llama-cpp
 prompt_template: "<|user|>\n{prompt}<|end|>\n<|assistant|>\n"