lighteternal commited on
Commit
ea87f9f
1 Parent(s): 5e7525f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -1
README.md CHANGED
@@ -10,7 +10,28 @@ tags:
10
  license: llama3
11
 
12
  ---
13
- # merge
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
 
15
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
16
 
 
10
  license: llama3
11
 
12
  ---
13
+ # Llama3-merge-biomed-8b
14
+
15
+ This is a DARE-TIES Merge of Llama3-8b-Instruct + NousResearch/Hermes-2-Pro-Llama-3-8B + aaditya/Llama3-OpenBioLLM-8B
16
+
17
+ ## Leaderboard metrics
18
+
19
+ | Task | Metric | Llama3-merge-biomed-8b (%) | Llama3-8B-Inst (%) | Llama3-OpenBioLLM-8B (%) |
20
+ |--------------------------------------|--------------------------|------------------|------------|-------------|
21
+ | **ARC Challenge** | Accuracy | 59.39 | 57.17 | 55.38 |
22
+ | | Normalized Accuracy | 63.65 | 60.75 | 58.62 |
23
+ | **Hellaswag** | Accuracy | 62.59 | 59.04 | 61.83 |
24
+ | | Normalized Accuracy | 81.53 | 78.55 | 80.76 |
25
+ | **Winogrande** | Accuracy | 75.93 | 74.51 | 70.88 |
26
+ | **GSM8K** | Accuracy | 59.36 | 68.69 | 10.16 |
27
+ | **HendrycksTest-Average** | Accuracy | 67.85 | 67.07 | 64.40 |
28
+ | | Normalized Accuracy | 67.85 | 67.07 | 64.40 |
29
+ | **HendrycksTest-Anatomy** | Accuracy | 72.59 | 65.19 | 56.30 |
30
+ | **HendrycksTest-Clinical Knowledge** | Accuracy | 77.83 | 74.72 | 60.38 |
31
+ | **HendrycksTest-College Biology** | Accuracy | 79.86 | 79.86 | 79.86 |
32
+ | **HendrycksTest-College Medicine** | Accuracy | 70.81 | 63.58 | 62.28 |
33
+ | **HendrycksTest-Medical Genetics** | Accuracy | 84.00 | 80.00 | 76.00 |
34
+ | **HendrycksTest-Professional Medicine** | Accuracy | 71.69 | 71.69 | 69.41 |
35
 
36
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
37