fix yaml desc

README.md

@@ -1,11 +1,13 @@
-# DeepSeek V3 - INT4 (TensorRT-LLM)
-
-This repository provides an INT4-quantized version of the DeepSeek V3 model, suitable for high-speed, memory-efficient inference with TensorRT-LLM.
-
 ---
+language:
+- en
 base_model:
 - deepseek-ai/DeepSeek-V3
+pipeline_tag: text-generation
 ---
+# DeepSeek V3 - INT4 (TensorRT-LLM)
+
+This repository provides an INT4-quantized version of the DeepSeek V3 model, suitable for high-speed, memory-efficient inference with TensorRT-LLM.
 
 
 Model Summary
@@ -36,4 +38,4 @@ trtllm-build --checkpoint_dir /DeepSeek-V3-int4-TensorRT  \
 
 ### Disclaimer:
 
-This model is a quantized checkpoint intended for research and experimentation with high-performance inference. Use at your own risk and validate outputs for production use-cases.
+This model is a quantized checkpoint intended for research and experimentation with high-performance inference. Use at your own risk and validate outputs for production use-cases.