honest v1 status: experimental, not yet reliable tool-caller

README.md

@@ -40,5 +40,17 @@ that gap on a tiny (≤2B, Tiny-Titan-class) model.
 Standard Qwen2.5 chat template with `tools=`. The model responds with
 `<tool_call>{"name": ..., "arguments": ...}</tool_call>` when a tool is warranted.
 
+## Status — experimental v1 ⚠️
+This first pass (1 epoch, `max_length=1024`, ~3.7k examples) **does not yet
+reliably emit `<tool_call>`** in free generation: teacher-forced token accuracy
+was 0.92, but greedy decoding is degenerate and sensitive to the prompt template
+(it was trained on the Hermes ChatML rendering, not Qwen's `apply_chat_template`
+output — a train/inference mismatch). Treat as a proof-of-pipeline, not a
+production tool-caller.
+
+Known fixes for v2: align train and inference templates (use
+`apply_chat_template(tools=...)` for both), more epochs, full sequence length,
+and a held-out eval on tool-call emission.
+
 ## License
 Apache-2.0 (inherits from the base model).