Update README.md

README.md

@@ -43,6 +43,11 @@ model-index:
 
 # SPID: Split-based Prompt Injection Detector
 
+<p align="center">
+  <img src="spid_architecture.png" width="85%">
+</p>
+
+
 **SPID** is a lightweight (184M, ~1.5GB) pre-filter that blocks common prompt injection attacks before they reach expensive LLM APIs. By catching obvious attacks locally—even on CPU—SPID reduces API costs while large LLMs handle legitimate traffic.
 
 The key innovation is **fragment-based detection**: SPID splits input into fragments and classifies each independently, catching compound attacks where a malicious instruction hides behind a benign prefix.
@@ -55,7 +60,7 @@ The key innovation is **fragment-based detection**: SPID splits input into fragm
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
-model_id = "your-username/spid-deberta-base"
+model_id = "JHC04567/spid-deberta-base"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForSequenceClassification.from_pretrained(model_id)