Update model.yml

model.yml

@@ -16,6 +16,7 @@ max_tokens: 4096 # Infer from base config.json -> max_position_embeddings
 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
 prompt_template: "{system_message} [INST] {prompt} [/INST]"