Adding Evaluation Results
#1
by
sethuiyer
- opened
README.md
CHANGED
@@ -99,4 +99,16 @@ SynthIQ's strengths can be succinctly summarized as follows:
|
|
99 |
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.
|
100 |
|
101 |
|
102 |
-
License is LLama2 license as uukuguy/speechless-mistral-six-in-one-7b is llama2 license.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
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.
|
100 |
|
101 |
|
102 |
+
License is LLama2 license as uukuguy/speechless-mistral-six-in-one-7b is llama2 license.
|
103 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
104 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sethuiyer__SynthIQ-7b)
|
105 |
+
|
106 |
+
| Metric | Value |
|
107 |
+
|-----------------------|---------------------------|
|
108 |
+
| Avg. | 69.37 |
|
109 |
+
| ARC (25-shot) | 65.87 |
|
110 |
+
| HellaSwag (10-shot) | 85.82 |
|
111 |
+
| MMLU (5-shot) | 64.75 |
|
112 |
+
| TruthfulQA (0-shot) | 57.0 |
|
113 |
+
| Winogrande (5-shot) | 78.69 |
|
114 |
+
| GSM8K (5-shot) | 64.06 |
|