Merge pull request #3051 from madeline-underwood/erie

Update documentation for ERNIE-4.5 setup: refine image alt text and e…

Author: jasonrandrews

content/learning-paths/cross-platform/ernie_moe_v9/2_llamacpp_installation.md

@@ -113,7 +113,7 @@ print_info: general.name     = Ernie-4.5-21B-A3B-Thinking
 
 Once inference is complete, the expected output looks like this (in Chinese):
 
-![Terminal output showing ERNIE-4.5 model response in Chinese with structured markdown formatting explaining Mixture of Experts concept alt-txt#center](meo_result.png "Introducing Mixture of Experts in Chinese")
+![Terminal output showing ERNIE-4.5 model response in Chinese with structured markdown formatting explaining Mixture of Experts concept#center](meo_result.png "Introducing Mixture of Experts in Chinese")
 
 This answer demonstrates the model's multilingual and structured reasoning ability. It begins with a narrative explanation introducing the concept of Mixture of Experts (MoE), followed by a well-organized markdown-style summary with section headers and bullet points. The response describes MoE as a model combining multiple specialized sub-models (experts) and a routing mechanism (gateway) to activate only a few experts per input. It explains how routing selects top experts based on input features and how the system reduces computation by activating only a small number of experts per token. The answer also gives examples such as word segmentation and translation, explaining how different experts might focus on distinct subtasks in Chinese NLP applications.
 

content/learning-paths/cross-platform/ernie_moe_v9/_index.md

@@ -5,6 +5,8 @@ minutes_to_complete: 60
 
 who_is_this_for: This is an advanced topic for developers and engineers who want to deploy Mixture of Experts (MoE) models, such as ERNIE 4.5, on edge devices. MoE architectures allow large LLMs with 21 billion or more parameters to run with only a fraction of their weights active per inference, making them ideal for resource constrained environments.
 
+description: Learn how to deploy ERNIE-4.5 Mixture of Experts models on Armv9 devices using llama.cpp, compare PT and Thinking variants, and measure Armv9-specific hardware optimization impact.
+
 learning_objectives:
     - Deploy MoE models like ERNIE-4.5 on edge devices using llama.cpp
     - Compare inference behavior between ERNIE-4.5 PT and Thinking versions