arielnlee commited on
Commit
c350af5
1 Parent(s): 93bdf93

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -10
README.md CHANGED
@@ -15,16 +15,6 @@ metrics:
15
 
16
  GPlatty-30B is a merge of [garage-bAInd/Platypus-30B](https://huggingface.co/lilloukas/Platypus-30B) and [chansung/gpt4-alpaca-lora-30b](https://huggingface.co/chansung/gpt4-alpaca-lora-30b)
17
 
18
- | Metric | Value |
19
- |-----------------------|-------|
20
- | MMLU (5-shot) | 63.6 |
21
- | ARC (25-shot) | 66.0 |
22
- | HellaSwag (10-shot) | 84.8 |
23
- | TruthfulQA (0-shot) | 53.8 |
24
- | Avg. | 67.0 |
25
-
26
- We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above.
27
-
28
  ## Model Details
29
 
30
  * **Trained by**: Platypus-30B trained by Cole Hunter & Ariel Lee; gpt4-alpaca-lora-30b by chansung.
 
15
 
16
  GPlatty-30B is a merge of [garage-bAInd/Platypus-30B](https://huggingface.co/lilloukas/Platypus-30B) and [chansung/gpt4-alpaca-lora-30b](https://huggingface.co/chansung/gpt4-alpaca-lora-30b)
17
 
 
 
 
 
 
 
 
 
 
 
18
  ## Model Details
19
 
20
  * **Trained by**: Platypus-30B trained by Cole Hunter & Ariel Lee; gpt4-alpaca-lora-30b by chansung.