Update README.md

README.md

@@ -9,8 +9,10 @@ The aim of this model is to retain the reasoning capabilities of <a href="https:
 
 As this model derives from Llama 3.1, the <a href="https://www.llama.com/llama3_1/license/">Llama 3.1 Community License Agreement</a> applies.
 
+Use the [DeepSeek Chat Prompt Template](https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device#deepseek-chat-template) with this model.
+
 ## 8B Safetensors BF16 format:
-Use with [transformers](https://huggingface.co/docs/transformers/en/index) as you would Llama 3.1
+Use with [transformers](https://huggingface.co/docs/transformers/en/index) as you would Llama 3.1, but use the [DeepSeek Chat Prompt Template](https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device#deepseek-chat-template) as you would with the original DeepSeek-R1-Distill-Llama models.
 
 Use model id ___BlueBeck/LlamaAligned-DeepSeekR1-Distill-8b___
 
@@ -31,7 +33,7 @@ Thanks to [mradermacher](https://huggingface.co/mradermacher) for converting the
 
 
 ## 70B Safetensors BF16 format:
-Use with [transformers](https://huggingface.co/docs/transformers/en/index) as you would Llama 3.3
+Use with [transformers](https://huggingface.co/docs/transformers/en/index) as you would Llama 3.3, but use the [DeepSeek Chat Prompt Template](https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device#deepseek-chat-template) as you would with the original DeepSeek-R1-Distill-Llama models.
 
 [Or download files from here](https://huggingface.co/BlueBeck/LlamaAligned-DeepSeekR1-Distill-70b/tree/main)