sethuiyer commited on
Commit
97f9cec
1 Parent(s): 5215ae6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -0
README.md CHANGED
@@ -46,6 +46,28 @@ dtype: bfloat16
46
 
47
  ```
48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  ### Usage:
50
  ```python
51
  from transformers import AutoTokenizer, AutoModelForCausalLM
 
46
 
47
  ```
48
 
49
+ # Comparision Against Dr.Samantha 7B
50
+
51
+ | Subject | Medichat-Llama3-8B Accuracy (%) | Dr. Samantha Accuracy (%) |
52
+ |-------------------------|---------------------------------|---------------------------|
53
+ | Clinical Knowledge | 71.70 | 52.83 |
54
+ | Medical Genetics | 78.00 | 49.00 |
55
+ | Human Aging | 70.40 | 58.29 |
56
+ | Human Sexuality | 73.28 | 55.73 |
57
+ | College Medicine | 62.43 | 38.73 |
58
+ | Anatomy | 64.44 | 41.48 |
59
+ | College Biology | 72.22 | 52.08 |
60
+ | High School Biology | 77.10 | 53.23 |
61
+ | Professional Medicine | 63.97 | 38.73 |
62
+ | Nutrition | 73.86 | 50.33 |
63
+ | Professional Psychology | 68.95 | 46.57 |
64
+ | Virology | 54.22 | 41.57 |
65
+ | High School Psychology | 83.67 | 66.60 |
66
+ | **Average** | **70.33** | **48.85** |
67
+
68
+
69
+ The current model demonstrates a substantial improvement over the previous [Dr. Samantha](sethuiyer/Dr_Samantha-7b) model in terms of subject-specific knowledge and accuracy.
70
+
71
  ### Usage:
72
  ```python
73
  from transformers import AutoTokenizer, AutoModelForCausalLM