Update README.md
Browse files
README.md
CHANGED
|
@@ -50,3 +50,16 @@ Jane: I am fine, thank you.</s>
|
|
| 50 |
## Why?
|
| 51 |
|
| 52 |
The purpose of all of these models is to act as a base for me to train on. This one so far has the best multi-turn conversational ability, and should get really good at following long-form conversations after a bit of tweaking.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
## Why?
|
| 51 |
|
| 52 |
The purpose of all of these models is to act as a base for me to train on. This one so far has the best multi-turn conversational ability, and should get really good at following long-form conversations after a bit of tweaking.
|
| 53 |
+
|
| 54 |
+
## Scores
|
| 55 |
+
Metric | Score
|
| 56 |
+
---|---
|
| 57 |
+
Average | 64.93
|
| 58 |
+
ARC | 64.16
|
| 59 |
+
HellaSwag | 84.37
|
| 60 |
+
MMLU | 60.38
|
| 61 |
+
TruthfulQA | 67.95
|
| 62 |
+
Winogrande | 76.72
|
| 63 |
+
GSM8K | 36.01
|
| 64 |
+
|
| 65 |
+
[Details](https://huggingface.co/datasets/open-llm-leaderboard/details_maldv__winter-garden-7b-delta)
|