Add README

README.md

@@ -0,0 +1,25 @@
+
+# Qwen3-32B Verilog LoRA Adapter
+
+This repository contains a LoRA adapter trained on the Qwen3-32B model for Verilog code generation. The adapter was trained using GRPO (Generalized Reinforcement Learning with Policy Optimization) on the VerilogEval dataset.
+
+## Model Details
+
+- **Base Model**: Qwen/Qwen3-32B
+- **Task**: Verilog Code Generation
+- **Training Method**: GRPO
+- **Framework**: vLLM
+
+## Usage with vLLM
+
+```bash
+python -m vllm.entrypoints.openai.api_server \
+    --model "Qwen/Qwen3-32B" \
+    --enable-lora \
+    --lora-modules verilog-sft="sonyashijin/qwen3-32b-verilog-lora" \
+    --max-loras 1 \
+    --max-lora-rank 32
+```
+
+## License
+Apache 2.0