Update README.md

tweaking the serve command.

README.md

@@ -95,16 +95,15 @@ For vLLM tool calling:
 vllm serve btbtyler09/Qwen3-Coder-Next-GPTQ-4bit \
   --tensor-parallel-size 4 \
   --trust-remote-code \
-  --quantization gptq \
+  --dtype float16 \
   --enable-auto-tool-choice \
-  --tool-call-parser hermes
+  --tool-call-parser qwen3_coder
 ```
 
 ## Credits
 
 - **Base Model**: [Qwen](https://huggingface.co/Qwen) - Qwen3-Coder-Next
 - **Quantization**: GPTQ via [GPTQModel](https://github.com/modelcloud/gptqmodel) v5.7.0
-- **Expert Converter**: Custom `convert_qwen3next_expert_converter` for fused 3D expert weights
 - **Quantized by**: [btbtyler09](https://huggingface.co/btbtyler09)
 
 ## License