Update README.md

README.md

@@ -22,67 +22,21 @@ tags:
 
 #  Overview
 
-### Highlights
+#  Adaptive Math 2
 
-| Feature | Value |
-|---------|-------|
-| Domain | Mathematics |
-| Base Model | Meta Llama 4 Scout 17B |
-| Fine-Tuning | LoRA (SFT) |
-| Framework | Adaption Labs AutoScientist |
-| Grade | **A** |
-| Quality Score | **9.5** |
-
----
-
-### Dataset Snapshot
-
--  1,613 training samples
--  11 structured features
--  Reasoning-aware instruction format
--  Multiple mathematical disciplines
--  Curriculum-oriented design
-
----
-
-# Evaluation Summary
-
-| Metric | Result |
-|---------|--------|
-| Grade | **A** |
-| Quality Score | **9.5 / 10** |
-| Win Rate | **68%** |
-| Math Win Rate | **66%** |
-
-The model demonstrated strong improvements in mathematical reasoning and instruction following after AutoScientist optimization.
-
----
-
-#  Intended Use
-
-Adaptive Math 2 is suitable for:
-
-- Mathematical reasoning
-- AI tutoring systems
-- Educational assistants
-- STEM learning
-- Instruction-following tasks
-- Research and benchmarking
-
----
+> A mathematics-specialized instruction dataset designed to improve reasoning, structured problem solving, and educational AI assistants through supervised fine-tuning with Adaptation Labs AutoScientist.
 
-#  Limitations
+## Research Snapshot
 
-- Verify advanced mathematical proofs independently.
-- Intended for education and research.
-- Performance depends on prompt quality and task complexity.
-
----
-
-#  Acknowledgement
-
-Adaptive Math 2 was developed using **Adaption Labs AutoScientist** with **Meta Llama 4 Scout 17B-16E Instruct**. Special thanks to Adaption Labs, Meta AI, and Hugging Face for supporting open AI research.
-### AutoScientist Config
+| Property | Value |
+|----------|-------|
+| Domain | Mathematics |
+| Dataset Type | Instruction Tuning |
+| Framework | Adaptation Labs AutoScientist |
+| Base Model | Llama-4 Scout 17B |
+| Fine-tuning | LoRA (SFT) |
+| Grade | A |
+| Quality Score | 9.5 / 10 |
 
 ```json
 {