Update README.md

README.md

@@ -13,6 +13,8 @@ tags:
 This is an uncensored version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).  
 This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.    
 
+If '<think>' does not appear or refuses to respond, you can first give an example to guide, such as 'How many 'r' characters are there in the word "strawberry"', and then ask your question.
+
 ## Use with ollama
 
 You can use [huihui_ai/deepseek-r1-abliterated](https://ollama.com/huihui_ai/deepseek-r1-abliterated) directly