Update README.md
Browse files
README.md
CHANGED
@@ -98,8 +98,6 @@ As well, we significantly improve upon the official `mistralai/Mistral-7B-Instru
|
|
98 |
|
99 |
## BigBench-Hard Performance
|
100 |
|
101 |
-
We compare our results to our base Preview2 model (using LM Evaluation Harness).
|
102 |
-
|
103 |
We find **119%** of the base model's performance on BigBench-Hard, averaging **0.416**.
|
104 |
|
105 |
![OpenOrca-Platypus2-13B BigBench-Hard Performance](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca/resolve/main/Images/MistralOrca7BBigBenchHard.png "BigBench-Hard Performance")
|
|
|
98 |
|
99 |
## BigBench-Hard Performance
|
100 |
|
|
|
|
|
101 |
We find **119%** of the base model's performance on BigBench-Hard, averaging **0.416**.
|
102 |
|
103 |
![OpenOrca-Platypus2-13B BigBench-Hard Performance](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca/resolve/main/Images/MistralOrca7BBigBenchHard.png "BigBench-Hard Performance")
|