Hugging Face's logo

HachiML
/
youri-2x7b_dev

Text Generation
Transformers
Safetensors
Japanese
mixtral
Mixture of Experts
text-generation-inference
Model card Files
xet
Community
HachiML commited on
Commit
eecb1c2
·
verified ·
1 Parent(s): 1a08d74

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -12,19 +12,19 @@ This model is a Mixture of Experts (MoE) merger of the following two models:
12
 
13
  | Model |JCommonsenseQA(3-shot,acc.)|JNLI(3-shot,balanced acc.)|MARC-ja(0-shot,balanced acc.)|JSQuAD(2-shot,F1)|4-AVERAGE|
14
  |----------------------------------------------------------------|------:|------:|---------:|-------:|------:|
15
- |[**youri-2x7b_dev**](https://huggingface.co/mlabonne/phixtral-2x2_8)| **91.15**| **71.03**| **95.90**| **91.30**| **87.34**|
16
  |[youri-7b-instruction](https://huggingface.co/rinna/youri-7b-instruction) *| 88.83| 63.56| 93.78| 92.19| 84.59|
17
  |[youri-7b-chat](https://huggingface.co/rinna/youri-7b-chat) *| 91.78| 70.35| 96.69| 79.62| 84.61|
18
 
19
  | Model |jaqket-v2(1-shot,F1)|xlsum(1-shot,ROUGE 2)|6-AVERAGE|
20
  |----------------------------------------------------------------|------:|------:|------:|
21
- |[**youri-2x7b_dev**](https://huggingface.co/mlabonne/phixtral-2x2_8)| **84.59**| **22.25**| **76.03**|
22
  |[youri-7b-instruction](https://huggingface.co/rinna/youri-7b-instruction) *| 83.92| 24.67| 75.13|
23
  |[youri-7b-chat](https://huggingface.co/rinna/youri-7b-chat) *| 83.71| 24.21| 75.33|
24
 
25
  | Model |xwinograd(0-shot,acc.)|mgsm(5-shot,acc.)|JCoLA(2-shot,balanced acc.)|9-AVERAGE|
26
  |----------------------------------------------------------------|------:|------:|---------:|------:|
27
- |[**youri-2x7b_dev**](https://huggingface.co/mlabonne/phixtral-2x2_8)| **81.43**| **22.00**| **59.84**| **68.83**|
28
  |[youri-7b-instruction](https://huggingface.co/rinna/youri-7b-instruction) *| 78.94 | 17.20| 54.04| 66.35|
29
  |[youri-7b-chat](https://huggingface.co/rinna/youri-7b-chat) *| 80.92| 25.20| 53.78| 67.36|
30
 
 
12
 
13
  | Model |JCommonsenseQA(3-shot,acc.)|JNLI(3-shot,balanced acc.)|MARC-ja(0-shot,balanced acc.)|JSQuAD(2-shot,F1)|4-AVERAGE|
14
  |----------------------------------------------------------------|------:|------:|---------:|-------:|------:|
15
+ |[**youri-2x7b_dev**](https://huggingface.co/HachiML/youri-2x7b_dev)| **91.15**| **71.03**| **95.90**| **91.30**| **87.34**|
16
  |[youri-7b-instruction](https://huggingface.co/rinna/youri-7b-instruction) *| 88.83| 63.56| 93.78| 92.19| 84.59|
17
  |[youri-7b-chat](https://huggingface.co/rinna/youri-7b-chat) *| 91.78| 70.35| 96.69| 79.62| 84.61|
18
 
19
  | Model |jaqket-v2(1-shot,F1)|xlsum(1-shot,ROUGE 2)|6-AVERAGE|
20
  |----------------------------------------------------------------|------:|------:|------:|
21
+ |[**youri-2x7b_dev**](https://huggingface.co/HachiML/youri-2x7b_dev)| **84.59**| **22.25**| **76.03**|
22
  |[youri-7b-instruction](https://huggingface.co/rinna/youri-7b-instruction) *| 83.92| 24.67| 75.13|
23
  |[youri-7b-chat](https://huggingface.co/rinna/youri-7b-chat) *| 83.71| 24.21| 75.33|
24
 
25
  | Model |xwinograd(0-shot,acc.)|mgsm(5-shot,acc.)|JCoLA(2-shot,balanced acc.)|9-AVERAGE|
26
  |----------------------------------------------------------------|------:|------:|---------:|------:|
27
+ |[**youri-2x7b_dev**](https://huggingface.co/HachiML/youri-2x7b_dev)| **81.43**| **22.00**| **59.84**| **68.83**|
28
  |[youri-7b-instruction](https://huggingface.co/rinna/youri-7b-instruction) *| 78.94 | 17.20| 54.04| 66.35|
29
  |[youri-7b-chat](https://huggingface.co/rinna/youri-7b-chat) *| 80.92| 25.20| 53.78| 67.36|
30