Hugging Face's logo

google
/
gemma-4-12B-it

Any-to-Any
Transformers
Safetensors
gemma4_unified
image-text-to-text
Eval Results
Model card Files
xet
 Community
35

fix: chat template — null handling, reasoning preservation, turn-tag balance, input validation

#35
by lucianommartins - opened
base: refs/heads/main
←
from: refs/pr/35
Discussion Files changed
+65
-41
lucianommartins
 Google org

Summary

Improves Gemma4 chat template:

Bug fixes

  • None values now render as null instead of Python's None
  • String-typed tool_calls[].function.arguments now raises a clear error instead of silently producing malformed DSL
  • Prior-turn reasoning/thinking is preserved across multi-turn tool-call chains (preserve_thinking flag, default=true)
  • Consecutive assistant messages now produce balanced <|turn>model/<turn|> tags via forward-scan continuation detection

Improvements

  • enable_thinking normalized once with | default(false), eliminating repetitive is defined and checks
  • image_url and input_audio content types now map to <|image|> and <|audio|> (OpenAI compatibility)
  • Empty messages=[] handled gracefully instead of crashing
  • Unmatched tool_call_id in tool responses falls back to 'unknown' instead of crashing
  • Consistent .get() access prevents StrictUndefined errors for optional message keys
  • O(1) backward scan for model-turn continuation (was O(n) per message)
fix: chat template — null handling, reasoning preservation, turn-tag balance, input validation14d9d4bc
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment