docs: update DeepSeek

Author: giladgd

docs/blog/v3.6-deepseek-r1.md

@@ -1,6 +1,6 @@
 ---
 title: DeepSeek R1 with function calling
-date: 2025-02-21T15:00:00Z
+date: 2025-02-21T19:00:00Z
 lastUpdated: false
 author:
     name: Gilad S.
@@ -90,6 +90,10 @@ Here are some recommended model URIs you can use to try out DeepSeek R1 with fun
 | [DeepSeek R1 Distill Qwen 14B](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-GGUF)   | 8.99GB | `hf:mradermacher/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M`  |
 | [DeepSeek R1 Distill Qwen 32B](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-GGUF)   | 19.9GB | `hf:mradermacher/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M`  |
 
+> The 7B model works well with function calling in the first prompt, but tends to deteriorate in subsequent queries.
+> <br/>
+> Use a larger model for better performance with multiple prompts.
+
 ::: info TIP
 Estimate the compatibility of a model with your machine before downloading it using the [`inspect estimate`](../cli/inspect/estimate.md) command:
 ```shell