add open llm leaderboard
Browse files
README.md
CHANGED
|
@@ -41,6 +41,10 @@ The code to train this model is available on [Google Colab](https://colab.resear
|
|
| 41 |
|
| 42 |
## Results
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
Teknium (author of OpenHermes-2.5-Mistral-7B) benchmarked the model ([see his tweet](https://twitter.com/Teknium1/status/1729955709377503660)).
|
| 45 |
|
| 46 |
Results are improved on every benchmark: **AGIEval** (from 43.07% to 43.62%), **GPT4All** (from 73.12% to 73.25%), and **TruthfulQA**.
|
|
|
|
| 41 |
|
| 42 |
## Results
|
| 43 |
|
| 44 |
+
**Update:** NeuralHermes-2.5 became the best Hermes-based model on the Open LLM leaderboard and one of the very best 7b models. 🎉
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
Teknium (author of OpenHermes-2.5-Mistral-7B) benchmarked the model ([see his tweet](https://twitter.com/Teknium1/status/1729955709377503660)).
|
| 49 |
|
| 50 |
Results are improved on every benchmark: **AGIEval** (from 43.07% to 43.62%), **GPT4All** (from 73.12% to 73.25%), and **TruthfulQA**.
|