Undi95 leaderboard-pr-bot commited on
Commit
c8ae0c6
1 Parent(s): 5952f55

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (314dc26be7639cdc816be74ec719c60adb133d58)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -3,4 +3,17 @@ license: cc-by-nc-4.0
3
  ---
4
  (0.70) NousResearch/Nous-Hermes-Llama2-13b & (0.30) jondurbin/airoboros-lmoe-13b-2.1/adapters/code
5
 
6
- Nous-Hermes-Llama2-13b merged with a LoRA at 0.30 weight.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
  (0.70) NousResearch/Nous-Hermes-Llama2-13b & (0.30) jondurbin/airoboros-lmoe-13b-2.1/adapters/code
5
 
6
+ Nous-Hermes-Llama2-13b merged with a LoRA at 0.30 weight.
7
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
8
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__Nous-Hermes-13B-Code)
9
+
10
+ | Metric | Value |
11
+ |-----------------------|---------------------------|
12
+ | Avg. | 51.98 |
13
+ | ARC (25-shot) | 61.18 |
14
+ | HellaSwag (10-shot) | 83.21 |
15
+ | MMLU (5-shot) | 55.13 |
16
+ | TruthfulQA (0-shot) | 50.56 |
17
+ | Winogrande (5-shot) | 75.14 |
18
+ | GSM8K (5-shot) | 10.39 |
19
+ | DROP (3-shot) | 28.28 |