Update reproduction instruction

README.md

@@ -132,9 +132,9 @@ llm = LLM(
 )
 ```
 
-### Training / Reproduction
+### Training
 
-To reproduce this checkpoint — or train your own DFlash draft head — launch the streaming training recipe with [NVIDIA Model Optimizer](https://github.com/NVIDIA/Model-Optimizer):
+See the following streaming recipe for [NVIDIA Model Optimizer](https://github.com/NVIDIA/Model-Optimizer) as a reference for training your own DFlash draft head:
 
 ```sh
 uv run launch.py --yaml examples/moonshotai/Kimi-K2.6/hf_streaming_dflash_multi_node.yaml --yes