Update README.md

README.md

@@ -31,7 +31,7 @@ WildReward is trained using **ordinal regression** (CORAL-like approach) on the
 - **Source:** WildChat - large-scale human-LLM interactions
 - **Labeling:** 5-point ordinal scale based on user satisfaction signals
 - **Filtering:** Two-stage refinement including implicit feedback mining and refusal validation
-- **License:** [Specify your dataset license]
+- **License:** MIT
 
 ## Usage
 
@@ -41,7 +41,7 @@ WildReward is trained using **ordinal regression** (CORAL-like approach) on the
 import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
-model_name = "yourusername/WildReward-4B"
+model_name = "THU-KEG/WildReward-4B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSequenceClassification.from_pretrained(model_name)