Hugging Face's logo

lighteternal
/
Llama3-merge-biomed-8b

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
lighteternal commited on
Commit
0de9507
·
verified ·
1 Parent(s): c09ab32

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -14
README.md CHANGED
@@ -24,20 +24,19 @@ I recommend using the prompt template of Llama3: https://llama.meta.com/docs/mod
24
 
25
  | Task | Metric | Ours (%) | Llama38BInstr. (%) |OpenBioLLM8B (%) |
26
  |--------------------------------------|--------------------------|------------------|------------|-------------|
27
- | **ARC Challenge** | Accuracy | 59.39 | 57.17 | 55.38 |
28
- | | Normalized Accuracy | 63.65 | 60.75 | 58.62 |
29
- | **Hellaswag** | Accuracy | 62.59 | 59.04 | 61.83 |
30
- | | Normalized Accuracy | 81.53 | 78.55 | 80.76 |
31
- | **Winogrande** | Accuracy | 75.93 | 74.51 | 70.88 |
32
- | **GSM8K** | Accuracy | 59.36 | 68.69 | 10.16 |
33
- | **HendrycksTest-Average** | Accuracy | 67.85 | 67.07 | 64.40 |
34
- | | Normalized Accuracy | 67.85 | 67.07 | 64.40 |
35
- | **HendrycksTest-Anatomy** | Accuracy | 72.59 | 65.19 | 56.30 |
36
- | **HendrycksTest-Clinical Knowledge** | Accuracy | 77.83 | 74.72 | 60.38 |
37
- | **HendrycksTest-College Biology** | Accuracy | 79.86 | 79.86 | 79.86 |
38
- | **HendrycksTest-College Medicine** | Accuracy | 70.81 | 63.58 | 62.28 |
39
- | **HendrycksTest-Medical Genetics** | Accuracy | 84.00 | 80.00 | 76.00 |
40
- | **HendrycksTest-Professional Medicine** | Accuracy | 71.69 | 71.69 | 69.41 |
41
 
42
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
43
 
 
24
 
25
  | Task | Metric | Ours (%) | Llama38BInstr. (%) |OpenBioLLM8B (%) |
26
  |--------------------------------------|--------------------------|------------------|------------|-------------|
27
+ | **ARC Challenge** | Accuracy | **59.39** | 57.17 | 55.38 |
28
+ | | Normalized Accuracy | **63.65** | 60.75 | 58.62 |
29
+ | **Hellaswag** | Accuracy | **62.59** | 59.04 | 61.83 |
30
+ | | Normalized Accuracy | **81.53** | 78.55 | 80.76 |
31
+ | **Winogrande** | Accuracy | **75.93** | 74.51 | 70.88 |
32
+ | **GSM8K** | Accuracy | 59.36 | **68.69** | 10.15 |
33
+ | **HendrycksTest-Anatomy** | Accuracy | **72.59** | 65.19 | 69.62 |
34
+ | **HendrycksTest-Clinical Knowledge** | Accuracy | **77.83** | 74.72 | 60.38 |
35
+ | **HendrycksTest-College Biology** | Accuracy | **81.94** | 79.86 | 79.86 |
36
+ | **HendrycksTest-College Medicine** | Accuracy | **69.36** | 63.58 | 70.52 |
37
+ | **HendrycksTest-Medical Genetics** | Accuracy | **86.00** | 80.00 | 80.00 |
38
+ | **HendrycksTest-Professional Medicine** | Accuracy | **77.94** | 71.69 | 77.94 |
39
+
 
40
 
41
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
42