Update model.yml

model.yml

@@ -14,7 +14,7 @@ max_tokens: 8192 # Infer from base config.json -> max_position_embeddings
 stream: true # true | false
 
 # Engine / Model Settings
-ngl: 32 # Infer from base config.json -> num_attention_heads
+ngl: 33 # Infer from base config.json -> num_attention_heads
 ctx_len: 8192 # Infer from base config.json -> max_position_embeddings
 engine: cortex.llamacpp
 prompt_template: "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"