Update README.md
Browse files
README.md
CHANGED
|
@@ -12,4 +12,19 @@ experts:
|
|
| 12 |
- "You are an helpful general-pupose assistant that specializes in info about Gianni Sanrochman"
|
| 13 |
- source_model: nvidia/Llama3-ChatQA-1.5-8B
|
| 14 |
positive_prompts:
|
| 15 |
-
- "You excel at retrieving and explaining complex topics, and RAG "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
- "You are an helpful general-pupose assistant that specializes in info about Gianni Sanrochman"
|
| 13 |
- source_model: nvidia/Llama3-ChatQA-1.5-8B
|
| 14 |
positive_prompts:
|
| 15 |
+
- "You excel at retrieving and explaining complex topics, and RAG "
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
| Metric | Value |
|
| 21 |
+
|----------------------------------------|---------|
|
| 22 |
+
| Avg. | 65.13 |
|
| 23 |
+
| AI2 Reasoning Challenge (25-Shot) | 62.80 |
|
| 24 |
+
| HellaSwag (10-Shot) | 83.60 |
|
| 25 |
+
| MMLU (5-Shot) | 65.13 |
|
| 26 |
+
| TruthfulQA (0-shot) | 50.41 |
|
| 27 |
+
| Winogrande (5-shot) | 77.27 |
|
| 28 |
+
| GSM8k (5-shot) | 58.68 |
|
| 29 |
+
|
| 30 |
+
|