Update README.md

README.md

@@ -142,14 +142,12 @@ The process is *beautifully* simple:
 
 Research-Reasoner-7B-v0.3 offers a comprehensive suite of capabilities tailored specifically for research planning:
 
-* **Dual-Output Structure**: Provides both detailed chain-of-thought reasoning tokens and concise answer tokens
-* **Cross-Domain Expertise**: Trained on diverse research topics spanning AI/ML, data science, computer science, cybersecurity, quantum computing, life sciences, engineering, environmental sciences, and social sciences
-* **Methodological Reasoning**: Excels at identifying appropriate research methodologies, data collection strategies, and analysis techniques
-* **Implementation Planning**: Offers practical insights on resource requirements, technical limitations, and execution strategies
-* **Evaluation Framework Design**: Helps establish clear success criteria and validation approaches for research outcomes
-* **Challenge Anticipation**: Proactively identifies potential obstacles, limitations, and ethical considerations
-* **Interdisciplinary Integration**: Particularly effective for projects bridging multiple domains or requiring novel methodological approaches
-* **Structured Output Format**: Consistently delivers well-organized, hierarchical research plans with clear section delineation
+* **Dual-Output Structure**: Provides both detailed reasoning and concise answers
+* **Cross-Domain Expertise**: Trained on diverse research topics spanning AI/ML, data science, computer science, life sciences, engineering, and social sciences
+* **Methodological Reasoning**: Identifies appropriate research methodologies and analysis techniques
+* **Implementation Planning**: Offers practical insights on resource requirements and execution strategies
+* **Challenge Anticipation**: Identifies potential obstacles and ethical considerations
+* **Structured Output Format**: Delivers well-organized, hierarchical research plans
 
 ## Use Cases
 
@@ -262,7 +260,7 @@ This repository contains everything you need to use and understand Research-Reas
 - **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
 - **Hardware**: 1 × NVIDIA A100 PCIe GPU
 - **Training Duration**: Around 4 hours
-- **Dataset Summary**: Custom curated dataset specifically for research planning
+- **Dataset Specifications**: Custom curated dataset specifically for research planning
   - **Total Token Count**: 5,840,200
   - **Total Sample Count**: 5,750
   - **Average Tokens Per Sample**: 1015.69