[DOCS] Port API ref link (#26200)

### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*

Author: tsavina

docs/articles_en/learn-openvino/llm_inference_guide/genai-guide.rst

@@ -317,7 +317,8 @@ OpenVINO GenAI Flavor includes the following API:
 
 * visibility  -  controls the visibility of the GenAI library.
 
-Learn more about API in the `GenAI repository <https://github.com/openvinotoolkit/openvino.genai/tree/master/src/cpp/include/openvino/genai>`__.
+
+Learn more in the `GenAI API reference <https://docs.openvino.ai/2024/api/genai_api/api.html>`__.
 
 Additional Resources
 ####################

docs/articles_en/openvino-workflow/model-optimization-guide/weight-compression.rst

@@ -7,10 +7,6 @@ Weight compression is a technique for enhancing the efficiency of models,
 especially those with large memory requirements. This method reduces the model's
 memory footprint, a crucial factor for Large Language Models (LLMs).
 
-Weight compression is a technique for enhancing the efficiency of models,
-especially those with large memory requirements. This method reduces the model's
-memory footprint, a crucial factor for Large Language Models (LLMs).
-
 Unlike full model quantization, where weights and activations are quantized,
 weight compression in `Neural Network Compression Framework (NNCF) <https://github.com/openvinotoolkit/nncf>`__
 only targets the model's weights. This approach allows the activations to remain as