KnutJaegersberg leaderboard-pr-bot commited on
Commit
12be0dc
1 Parent(s): 1134d31

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (e4f4fba1eb116822736146b5701a0f8c07ac3a4a)


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
@@ -6,4 +6,17 @@ This is just a standard conversion to hf transformers format of models from here
6
 
7
  https://huggingface.co/BlinkDL/rwkv-4-pileplus
8
 
9
- According to the documentation I found, this model should have seen roundabout 2 trillion tokens!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
 
7
  https://huggingface.co/BlinkDL/rwkv-4-pileplus
8
 
9
+ According to the documentation I found, this model should have seen roundabout 2 trillion tokens!
10
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
11
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__RWKV-4-PilePlus-169M-20230520-done-ctx4096)
12
+
13
+ | Metric | Value |
14
+ |-----------------------|---------------------------|
15
+ | Avg. | 25.0 |
16
+ | ARC (25-shot) | 23.98 |
17
+ | HellaSwag (10-shot) | 32.25 |
18
+ | MMLU (5-shot) | 23.37 |
19
+ | TruthfulQA (0-shot) | 42.29 |
20
+ | Winogrande (5-shot) | 49.17 |
21
+ | GSM8K (5-shot) | 0.38 |
22
+ | DROP (3-shot) | 3.53 |