From 0c31f41536e4d26a1bf8c0628230f928957c4ae2 Mon Sep 17 00:00:00 2001 From: Georgios Balikas Date: Thu, 2 Jan 2025 14:15:44 +0100 Subject: [PATCH] fix docstring --- src/smolagents/models.py | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/src/smolagents/models.py b/src/smolagents/models.py index 06b54df..ccee8c3 100644 --- a/src/smolagents/models.py +++ b/src/smolagents/models.py @@ -188,14 +188,12 @@ class HfApiModel(Model): This engine allows you to communicate with Hugging Face's models using the Inference API. It can be used in both serverless mode or with a dedicated endpoint, supporting features like stop sequences and grammar customization. Parameters: - model (`str`, *optional*, defaults to `"Qwen/Qwen2.5-Coder-32B-Instruct"`): + model_id (`str`, *optional*, defaults to `"Qwen/Qwen2.5-Coder-32B-Instruct"`): The Hugging Face model ID to be used for inference. This can be a path or model identifier from the Hugging Face model hub. token (`str`, *optional*): Token used by the Hugging Face API for authentication. This token need to be authorized 'Make calls to the serverless Inference API'. If the model is gated (like Llama-3 models), the token also needs 'Read access to contents of all public gated repos you can access'. If not provided, the class will try to use environment variable 'HF_TOKEN', else use the token stored in the Hugging Face CLI configuration. - max_tokens (`int`, *optional*, defaults to 1500): - The maximum number of tokens allowed in the output. timeout (`int`, *optional*, defaults to 120): Timeout for the API request, in seconds.