make it clear you need to make a chat template jinja file

README.md

@@ -359,9 +359,16 @@ numactl -N "$SOCKET" -m "$SOCKET" \
     --jinja
 ```
 
-For tool use you can always bring your own template with `--chat-template-file myTemplate.jinja` and might need `--special` etc. The chat template baked into these GGUFs from the [original one](https://huggingface.co/stepfun-ai/Step-3.5-Flash/blob/main/chat_template.jinja).
-
-Check [Discussion 1 for a tested working chat template for tool use thanks to mindkrypted](https://huggingface.co/ubergarm/Step-3.5-Flash-GGUF/discussions/1#69878ca7ae66ac235fc2ca95)!
+The chat template baked into these GGUFs from the [original
+one](https://huggingface.co/stepfun-ai/Step-3.5-Flash/blob/main/chat_template.jinja).
+Because of [this note and later updated official gguf chat
+template](https://huggingface.co/stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S/discussions/16)
+you will probably want to copy paste the template
+from the [official gguf chat
+template](https://huggingface.co/stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S/blob/main/step3p5_flash_Q4_K_S-00001-of-00012.gguf)
+and use `--chat-template-file myTemplate.jinja`.
+
+Also Check [Discussion 1 for a tested working chat template for tool use thanks to mindkrypted](https://huggingface.co/ubergarm/Step-3.5-Flash-GGUF/discussions/1#69878ca7ae66ac235fc2ca95)!
 
 Another option for mainline tool calling users is to check out [pwilkin's autoparser branch](https://github.com/ggml-org/llama.cpp/pull/18675).