From 18c68c4950f46864aa38fba020908701437e9e3d Mon Sep 17 00:00:00 2001 From: Suraj Subramanian Date: Mon, 7 Apr 2025 11:26:34 -0700 Subject: [PATCH] clarifying wording on tool & ipython --- llama_stack/models/llama/llama4/prompts.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama_stack/models/llama/llama4/prompts.py b/llama_stack/models/llama/llama4/prompts.py index ef6992979..5025482eb 100644 --- a/llama_stack/models/llama/llama4/prompts.py +++ b/llama_stack/models/llama/llama4/prompts.py @@ -61,7 +61,7 @@ def usecases(base_model: bool = False) -> List[UseCase | str]: - `system`: Sets the context in which to interact with the AI model. It typically includes rules, guidelines, or necessary information that helps the model respond effectively. - `user`: Represents the human interacting with the model. It includes the inputs, commands, and questions to the model. - `assistant`: Represents the response generated by the AI model based on the context provided in the `system`, `tool` and `user` prompts. - - `tool`: Represents the output of a tool call when sent back to the model from the executor. (The actual token used by the model is `<|ipython|>`.) + - `tool`: Represents the output of a tool call when sent back to the model from the executor. Note that the role name used in the prompt template is `ipython`; scroll down to the last example to see how this is used. """ ), ]