Update README.md

README.md

@@ -13,8 +13,13 @@ datasets:
 
 # Model Card for Router
 
-This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This model is fine-tuned to serve as a router for reasoning tasks, classifying input queries into one of three categories:
+
+  no_reasoning – Direct factual lookup or simple recall (e.g., "What is the capital of France?")
+  
+  low_reasoning – Requires light reasoning such as simple arithmetic, comparisons, or single logical steps (e.g., "If John has 5 apples and eats 2, how many are left?")
+  
+  high_reasoning – Requires multi-step reasoning, deep logical chains, or complex problem-solving (e.g., "Prove that the sum of two even numbers is always even").
 
 ## Quick start
 
@@ -28,12 +33,24 @@ messages = [
 pipe(messages)
 ```
 
-## Training procedure
+## Training Details
+
+Method: Supervised fine-tuning with SFTTrainer
+
+Objective: Multi-class classification with labels (no_reasoning, low_reasoning, high_reasoning)
+
+Dataset: Custom dataset of queries annotated with reasoning levels.
+
+
+
+
+## Limitations & Bias
 
- 
+May misclassify borderline queries (e.g., between low_reasoning and high_reasoning).
 
+Performance depends on the diversity of training data.
 
-This model was trained with SFT
+Inherits any biases from the base Gemma 3 270M model.
 
 ### Framework versions