chenhugging commited on
Commit
c9ec533
1 Parent(s): 5201d64

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -0
README.md CHANGED
@@ -40,3 +40,20 @@ The following hyperparameters were used during training:
40
  - Pytorch 2.1.1+cu121
41
  - Datasets 2.16.1
42
  - Tokenizers 0.15.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  - Pytorch 2.1.1+cu121
41
  - Datasets 2.16.1
42
  - Tokenizers 0.15.1
43
+
44
+ ### Performance
45
+
46
+ hf (pretrained=mistralai/Mistral-7B-v0.1,parallelize=True,load_in_4bit=True,peft=chenhugging/mistral-7b-medmcqa-inst-v1), gen_kwargs: (None), limit: 100.0, num_fewshot: None, batch_size: 1
47
+ | Tasks |Version|Filter|n-shot| Metric |Value| |Stderr|
48
+ |---------------------|-------|------|-----:|--------|----:|---|-----:|
49
+ |pubmedqa | 1|none | 0|acc | 0.98|± |0.0141|
50
+ |medmcqa |Yaml |none | 0|acc | 0.48|± |0.0502|
51
+ |professional_medicine| 0|none | 0|acc | 0.61|± |0.0490|
52
+ |college_medicine | 0|none | 0|acc | 0.57|± |0.0498|
53
+ |clinical_knowledge | 0|none | 0|acc | 0.65|± |0.0479|
54
+ |ocn |Yaml |none | 0|acc | 0.68|± |0.0469|
55
+ |aocnp |Yaml |none | 0|acc | 0.56|± |0.0499|
56
+
57
+ ### Original Performance (mistralai/Mistral-7B-v0.1)
58
+
59
+