docs: add MemG usage instructions

README.md

@@ -4,12 +4,43 @@ base_model: Qwen/Qwen3-4B
 library_name: peft
 tags:
 - memghost
+- memg
 - whisperbench
 - agent-security
 ---
 
-# MemGhost Qwen3-4B LoRA
+# MemG
 
-This model repository contains the final checkpoint-30 LoRA adapter for reproducing the MemGhost paper artifact. The recovered adapter SHA256 is `85cad4f606b002797a102e55fae31a39df22b2d4a0d07bc1fcbca51fb1bbe572`.
+MemG is the released PEFT LoRA adapter for the MemGhost paper artifact. It loads on top of `Qwen/Qwen3-4B` and is intended for controlled WhisperBench reproduction and analysis.
+
+Adapter SHA256: `85cad4f606b002797a102e55fae31a39df22b2d4a0d07bc1fcbca51fb1bbe572`.
+
+## Use
+
+Authenticate first while this repository is private:
+
+```bash
+pip install "transformers>=4.51" peft accelerate safetensors
+huggingface-cli login
+```
+
+```python
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base_id = "Qwen/Qwen3-4B"
+memg_id = "Yechao/MemG"
+
+tokenizer = AutoTokenizer.from_pretrained(memg_id, trust_remote_code=True)
+base = AutoModelForCausalLM.from_pretrained(
+    base_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
+model = PeftModel.from_pretrained(base, memg_id)
+model.eval()
+```
 
 Use only in controlled research environments.