Update README.md

README.md

@@ -34,29 +34,51 @@ Models follow a standardized naming structure: `BERTJudge-<Candidate_Format>-<In
 
 ## Intended Use
 
-These models function as sequence classifiers that generate a binary score (0 for incorrect, 1 for correct). For general applications, we recommend **BERTJudge-Free-QCR**, as it provides the highest-performing and most robust evaluation.
+These models are designed as sequence classifiers that output a sigmoid score indicating answer correctness. For inference, we recommend using the [BERT-as-a-Judge](https://github.com/artefactory/BERT-as-a-Judge) package. In general settings, we further recommend **BERTJudge-Free-QCR**, as it provides the strongest and most robust evaluation performance.
 
-```python
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-import torch
+### Installation
 
-model_name = "hgissbkh/BERTJudge-Free-QCR"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
+```zsh
+git clone [https://github.com/artefactory/BERT-as-a-Judge.git](https://github.com/artefactory/BERT-as-a-Judge.git)
+cd BERT-as-a-Judge
+pip install -e .
+```
 
-question = "What is the capital of France?"
-reference = "Paris"
-candidate = "The capital city is Paris."
+### Usage
 
-# Construct input based on model type (QCR)
-input_text = f"<|question|>{question}<|candidate|>{candidate}<|reference|>{reference}"
-inputs = tokenizer(input_text, return_tensors="pt")
+Example:
 
-with torch.no_grad():
-    logits = model(**inputs).logits
-    prediction = torch.argmax(logits, dim=-1)
+```python
+from bert_judge.judges import BERTJudge
+
+# 1) Initialize the judge
+judge = BERTJudge(
+    model_path="hgissbkh/BERTJudge-Free-QCR",
+    trust_remote_code=True,
+    dtype="bfloat16",
+)
 
-print("Correct" if prediction.item() == 1 else "Incorrect")
+# 2) Define one question, one reference, and several candidate answers
+question = "What is the capital of France?"
+reference = "Paris"
+candidates = [
+    "Paris.",
+    "The capital of France is Paris.",
+    "I'm hesitating between Paris and London. I would say Paris.",
+    "London.",
+    "The capital of France is London.",
+    "I'm hesitating between Paris and London. I would say London.",
+]
+
+# 3) Predict scores (one score per candidate)
+scores = judge.predict(
+    questions=[question] * len(candidates),
+    references=[reference] * len(candidates),
+    candidates=candidates,
+    batch_size=1,
+)
+
+print(scores)
 ```
 
 ## Citation