Update model.yml

model.yml

@@ -16,4 +16,4 @@ stream: true # true | false
 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]"
+prompt_template: "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"