Update README.md

README.md

@@ -30,6 +30,14 @@ datasets:
 
 This is SynthIQ, rated 92.23/100 by GPT-4 across varied complex prompts. I used [mergekit](https://github.com/cg123/mergekit) to merge models.
 
+Metrics from OpenLLM leaderboard:
+
+| Model                                    | Average | ARC   | HellaSwag | MMLU  | TruthfulQA | Winogrande | GSM8K  |
+| ---------------------------------------- | ------- | ----- | --------- | ----- | ---------- | ---------- | ------ |
+| Weyaxi/OpenHermes-2.5_neural-chat-v3-3-openchat-5-1210-Slerp | 71.26   | 67.92 | 86.32     | 65.47 | 56.45      | 79.72      | 71.72  |
+| sethuiyer/SynthIO-7b                    | 69.37   | 65.87 | 85.82     | 64.75 | 57         | 78.69      | 64.06  |
+| uukuguy/speechless-mistral-six-in-one-7b | 60.76   | 62.97 | 84.6      | 63.29 | 57.77      | 77.51      | 18.42  |
+
 
 # Yaml Config
 
@@ -72,30 +80,23 @@ dtype: bfloat16
 
 <!-- prompt-template end -->
 
-## Evaluation by GPT-4
-Based on the evaluations of SynthIQ's performance across various prompts and its ability to handle a wide range of tasks, I would rate its overall performance at around 92.33/100. Here are ten points highlighting its strengths:
-
-1. **Versatility**: SynthIQ has demonstrated an impressive ability to tackle a diverse array of tasks, ranging from technical coding challenges to creative writing and philosophical discussions.
-
-2. **Technical Proficiency**: In programming-related prompts, SynthIQ showed a strong understanding of different programming languages and their practical applications.
-
-3. **Analytical Skills**: SynthIQ effectively dissected complex topics, providing logical, well-reasoned answers, particularly in technical and scientific explanations.
+SynthIQ's strengths can be succinctly summarized as follows:
 
-4. **Creative Intelligence**: The model displayed a notable creative flair, especially evident in tasks requiring storytelling, poetry writing, and imaginative scenarios.
+1. **Advanced Natural Language Processing**: SynthIQ excels in understanding and generating natural language, making it highly effective for conversational AI applications.
 
-5. **Effective Communication**: SynthIQ's responses were generally clear, well-structured, and articulate, showcasing its ability to communicate complex ideas effectively.
+2. **Strong Commonsense Reasoning**: It demonstrates a solid grasp of everyday scenarios and contexts, essential for practical and real-world applications.
 
-6. **Engagement with Cultural and Fictional Contexts**: The model adeptly handled prompts involving fictional characters and scenarios, demonstrating an understanding of various cultural and fictional contexts.
+3. **Creative and Engaging Content Generation**: SynthIQ has the capability to produce creative content, useful in fields like marketing, creative writing, and social media engagement.
 
-7. **Empathy in Responses**: SynthIQ showed a degree of emotional intelligence, especially in responses requiring empathy and understanding of human emotions.
+4. **Adaptive User Interaction**: It can effectively adapt to various user personas, providing personalized experiences and recommendations.
 
-8. **Problem-Solving Approach**: In prompts requiring problem-solving, SynthIQ exhibited a structured and methodical approach, showcasing its capability in developing solutions.
+5. **Multitasking Across Languages and Subjects**: SynthIQ is adept at handling tasks across different languages and subjects, showcasing its versatility in global and multifaceted settings.
 
-9. **Adaptability**: The model adapted well to different styles and tones, whether responding in the style of a character like Iron Man or addressing a technical audience.
+6. **Analytical and Problem-Solving Skills**: The model shows proficiency in analytical reasoning and problem-solving, applicable in data-driven decision-making and complex scenario analysis.
 
-10. **Integration of Interdisciplinary Knowledge**: SynthIQ effectively integrated knowledge from different domains, such as combining technical expertise with creative or ethical considerations.
+7. **Cultural and Contextual Awareness**: SynthIQ's awareness of different cultural and social contexts makes it suitable for applications requiring cultural sensitivity.
 
-Overall, SynthIQ's performance is indicative of a highly capable and multifaceted AI model. Its proficiency in both analytical and creative domains, coupled with effective communication skills, makes it well-suited for a wide range of applications. While there is room for improvement, particularly in areas requiring deep emotional understanding or highly nuanced creativity, its overall performance is impressive.
+8. **Empathetic and Human-Like Interactions**: The model can engage in empathetic and human-like dialogues, ideal for applications in mental health support, customer service, and education.
 
 
 License is LLama2 license as uukuguy/speechless-mistral-six-in-one-7b is llama2 license.