Update README.md

README.md

@@ -8,50 +8,11 @@ tags:
 - vllm
 ---
 
-# UserGRPO Model
+# UserGRPO Model for Retail Simulations
 
-UserGRPO model from https://arxiv.org/html/2605.08334v1
+UserGRPO checkpoint based on Gemma-3 for agent simulations in [SalesSim](https://arxiv.org/html/2605.08334v1). This model has been trained to adhere to persona specifications in dialogue-based retail simulations, as specified by preferences and dealbreakers. 
 
-## Files
 
-- `adapter_model.safetensors`: LoRA adapter weights
-- `adapter_config.json`: PEFT adapter configuration
+## License
 
-## Serving with vLLM
-
-This adapter can be served with vLLM by loading the Gemma 3 base model and enabling the LoRA module from this repository.
-
-```bash
-PORT=8071
-GPU=0
-MODEL_ID=google/gemma-3-4b-it
-SERVED_MODEL_NAME=gemma3_with_reasoning
-ADAPTER_REPO=sscollab2/gemma3_checkpoint_step100
-
-CUDA_VISIBLE_DEVICES="$GPU" vllm serve "$MODEL_ID" \
-  --host 0.0.0.0 \
-  --port "$PORT" \
-  --tensor-parallel-size 1 \
-  --gpu-memory-utilization 0.90 \
-  --max-model-len 32768 \
-  --served-model-name gemma3_base \
-  --enable-lora \
-  --lora-modules "${SERVED_MODEL_NAME}=${ADAPTER_REPO}" \
-  --max-lora-rank 16 \
-  --enable-auto-tool-choice \
-  --tool-call-parser hermes \
-  --limit-mm-per-prompt '{"image":10,"audio":0}'
-```
-
-Once the server is ready, call the LoRA-served model name:
-
-```bash
-curl http://127.0.0.1:8071/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "gemma3_with_reasoning",
-    "messages": [
-      {"role": "user", "content": "Hello!"}
-    ]
-  }'
-```
+CC-BY-NC 4.0