InferenceIllusionist
commited on
Commit
•
3aebbd1
1
Parent(s):
3ec4751
Added open llm benchmark results table.
Browse files
README.md
CHANGED
@@ -19,7 +19,13 @@ A linear merge of:
|
|
19 |
|
20 |
These three models showed excellent acumen in technical topics so I wanted to see how they would behave together in a merge. Several different ratios were tested before this release, in the end a higher weighting for merlinite-7b helped smooth out some edges. This model is a test of how LAB tuning is impacted by merges with models leveraging DPO.
|
21 |
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
This was my first experiment with merging models so any feedback is greatly appreciated.
|
25 |
|
|
|
19 |
|
20 |
These three models showed excellent acumen in technical topics so I wanted to see how they would behave together in a merge. Several different ratios were tested before this release, in the end a higher weighting for merlinite-7b helped smooth out some edges. This model is a test of how LAB tuning is impacted by merges with models leveraging DPO.
|
21 |
|
22 |
+
### Benchmark Performance
|
23 |
+
| Name | Avg. | ARC | HellaSwag | MMLU | TruthfulQA | Winograde | GSM8K |
|
24 |
+
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
|
25 |
+
| <b>Magic-Dolphin-7b</b> | <u><b>67.48</b></u> | 65.78 | 85.61 | 64.64 | 58.01 | <u><b>79.64</b></u> | <u><b>51.18</b></u> |
|
26 |
+
| dolphin-2.6-mistral-7b-dpo-laser | 67.28 | 66.3 | 85.73 | 63.16 | 61.71 | 79.16 | 47.61 |
|
27 |
+
| merlinite-7b | N/A | 63.99 | 84.37 | 64.88 | N/A | 78.24 | N/A |
|
28 |
+
| Hyperion-1.5-Mistral-7B | 61.43 | 60.49 | 83.64 | 63.57 | 41.78 | 78.61 | 40.49 |
|
29 |
|
30 |
This was my first experiment with merging models so any feedback is greatly appreciated.
|
31 |
|