Upload README.md with huggingface_hub

README.md

@@ -74,8 +74,11 @@ per-projection mixed-dtype dispatch were added to hipfire for this model.
 ## Usage (hipfire)
 
 ```
-hipfire serve --model MiniMax-M2.7.mq2-lloyd
-# or a single forward:
+# Chat serving — these tiers were quantized before the chat-template auto-embed
+# fix, so point the daemon at the bundled template (chat_template.jinja, in this repo):
+HIPFIRE_JINJA_CHAT=1 HIPFIRE_CHAT_TEMPLATE_FILE=chat_template.jinja \
+  hipfire serve --model MiniMax-M2.7.mq2-lloyd
+# or a single raw forward (no chat template):
 # examples/infer_minimax --model MiniMax-M2.7.mq2-lloyd --prompt "..."
 ```