Adding Evaluation Results

#1
Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -30,3 +30,17 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
30
  tokenizer = AutoTokenizer.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied", use_fast=False)
31
  model = AutoModelForCausalLM.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied").cuda()
32
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  tokenizer = AutoTokenizer.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied", use_fast=False)
31
  model = AutoModelForCausalLM.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied").cuda()
32
  ```
33
+
34
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
35
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_hiyouga__Baichuan2-7B-Base-LLaMAfied)
36
+
37
+ | Metric | Value |
38
+ |-----------------------|---------------------------|
39
+ | Avg. | 42.83 |
40
+ | ARC (25-shot) | 49.57 |
41
+ | HellaSwag (10-shot) | 73.45 |
42
+ | MMLU (5-shot) | 54.86 |
43
+ | TruthfulQA (0-shot) | 37.54 |
44
+ | Winogrande (5-shot) | 70.72 |
45
+ | GSM8K (5-shot) | 7.81 |
46
+ | DROP (3-shot) | 5.85 |