ChuckMcSneed
commited on
Commit
•
ac11ad8
1
Parent(s):
b3767a6
Update README.md
Browse files
README.md
CHANGED
@@ -73,4 +73,13 @@ Then I SLERP-merged it with cognitivecomputations/dolphin-2.2-70b (Needed to bri
|
|
73 |
| D | 3 |
|
74 |
| S | 7.5 |
|
75 |
| P | 5.25 |
|
76 |
-
| Total | 19.75 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
| D | 3 |
|
74 |
| S | 7.5 |
|
75 |
| P | 5.25 |
|
76 |
+
| Total | 19.75 |
|
77 |
+
|
78 |
+
### Open LLM leaderboard
|
79 |
+
[Leaderboard on Huggingface](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
80 |
+
|Model |Average|ARC |HellaSwag|MMLU |TruthfulQA|Winogrande|GSM8K|
|
81 |
+
|--------------------------------|-------|-----|---------|-----|----------|----------|-----|
|
82 |
+
|ChuckMcSneed/Gembo-v1-70b |70.51 |71.25|86.98 |70.85|63.25 |80.51 |50.19|
|
83 |
+
|ChuckMcSneed/SMaxxxer-v1-70b |72.23 |70.65|88.02 |70.55|60.7 |82.87 |60.58|
|
84 |
+
|
85 |
+
Looks like adding a shitton of RP stuff decreased HellaSwag, WinoGrande and GSM8K, but increased MMLU and ARC. Interesting.
|