gte-small-ggml / README.md
maikaarda's picture
Update README.md
13d11c4
metadata
license: mit

ggml files of thenlper/gte-small

You can use this ggml for https://github.com/skeskinen/bert.cpp

gte-small

Data Type STSBenchmark eval time EmotionClassification eval time
f32 0.8554 12.40 0.4808 26.39
f16 0.8555 11.29 0.4808 18.48
q4_0 0.8537 9.22 0.4860 43.92
q4_1 0.8543 10.01 0.4832 38.33

all-MiniLM-L12-v2

Data Type STSBenchmark eval time EmotionClassification eval time
f32 0.8306 13.36 0.4117 21.23
f16 0.8306 11.51 0.4119 20.08
q4_0 0.8310 11.27 0.4183 20.81
q4_1 0.8325 12.37 0.4093 19.38

all-MiniLM-L6-v2

Data Type STSBenchmark eval time EmotionClassification eval time
f32 0.8201 6.83 0.4082 11.34
f16 0.8201 6.17 0.4085 10.28
q4_0 0.8175 5.45 0.3911 10.63
q4_1 0.8223 6.79 0.4027 11.41

bert-base-uncased

Data Type STSBenchmark eval time EmotionClassification eval time
f32 0.4738 52.38 0.3361 88.56
f16 0.4739 33.24 0.3361 55.86
q4_0 0.4940 33.93 0.3375 57.82
q4_1 0.4612 36.86 0.3318 59.63