83 lines
3.2 KiB
YAML
83 lines
3.2 KiB
YAML
model_name: Tucano2-qwen-1.5B-Base
|
|
results:
|
|
niah_pt_multikey_1_1024: 0.516
|
|
niah_pt_multikey_1_1024_stderr: 0.022371610982580396
|
|
niah_pt_multikey_1_2048: 0.444
|
|
niah_pt_multikey_1_2048_stderr: 0.022242244375731048
|
|
niah_pt_multikey_1_4096: 0.296
|
|
niah_pt_multikey_1_4096_stderr: N/A
|
|
niah_pt_multikey_1_alias: " - niah_pt_multikey_1"
|
|
niah_pt_multikey_2_1024: 0.064
|
|
niah_pt_multikey_2_1024_stderr: 0.01095664621097098
|
|
niah_pt_multikey_2_2048: 0.012
|
|
niah_pt_multikey_2_2048_stderr: 0.0048743737072649805
|
|
niah_pt_multikey_2_4096: 0.024
|
|
niah_pt_multikey_2_4096_stderr: N/A
|
|
niah_pt_multikey_2_alias: " - niah_pt_multikey_2"
|
|
niah_pt_multikey_3_1024: 0.57
|
|
niah_pt_multikey_3_1024_stderr: 0.022162634426652866
|
|
niah_pt_multikey_3_2048: 0.382
|
|
niah_pt_multikey_3_2048_stderr: 0.02175082059125093
|
|
niah_pt_multikey_3_4096: 0.254
|
|
niah_pt_multikey_3_4096_stderr: N/A
|
|
niah_pt_multikey_3_alias: " - niah_pt_multikey_3"
|
|
niah_pt_multiquery_1024: 0.162
|
|
niah_pt_multiquery_1024_stderr: 0.011325570055151673
|
|
niah_pt_multiquery_2048: 0.0385
|
|
niah_pt_multiquery_2048_stderr: 0.0059461090155537594
|
|
niah_pt_multiquery_4096: 0.0295
|
|
niah_pt_multiquery_4096_stderr: N/A
|
|
niah_pt_multiquery_alias: " - niah_pt_multiquery"
|
|
niah_pt_multivalue_1024: 0.0985
|
|
niah_pt_multivalue_1024_stderr: 0.008944579980191584
|
|
niah_pt_multivalue_2048: 0.025
|
|
niah_pt_multivalue_2048_stderr: 0.004721714643893329
|
|
niah_pt_multivalue_4096: 0.0335
|
|
niah_pt_multivalue_4096_stderr: N/A
|
|
niah_pt_multivalue_alias: " - niah_pt_multivalue"
|
|
niah_pt_single_1_1024: 0.066
|
|
niah_pt_single_1_1024_stderr: 0.011114633153652916
|
|
niah_pt_single_1_2048: 0.058
|
|
niah_pt_single_1_2048_stderr: 0.010463793860924815
|
|
niah_pt_single_1_4096: 0.058
|
|
niah_pt_single_1_4096_stderr: N/A
|
|
niah_pt_single_1_alias: " - niah_pt_single_1"
|
|
niah_pt_single_2_1024: 0.602
|
|
niah_pt_single_2_1024_stderr: 0.021912377885779953
|
|
niah_pt_single_2_2048: 0.466
|
|
niah_pt_single_2_2048_stderr: 0.022331264423258324
|
|
niah_pt_single_2_4096: 0.452
|
|
niah_pt_single_2_4096_stderr: N/A
|
|
niah_pt_single_2_alias: " - niah_pt_single_2"
|
|
niah_pt_single_3_1024: 0.496
|
|
niah_pt_single_3_1024_stderr: 0.022382357781962105
|
|
niah_pt_single_3_2048: 0.472
|
|
niah_pt_single_3_2048_stderr: 0.022347949832668024
|
|
niah_pt_single_3_4096: 0.43
|
|
niah_pt_single_3_4096_stderr: N/A
|
|
niah_pt_single_3_alias: " - niah_pt_single_3"
|
|
ruler_pt_4096: 0.28358181818181816
|
|
ruler_pt_4096_stderr: N/A
|
|
ruler_pt_alias: ruler_pt
|
|
ruler_pt_cwe_1024: 0.3368
|
|
ruler_pt_cwe_1024_stderr: 0.010680808928106402
|
|
ruler_pt_cwe_2048: 0.18159999999999998
|
|
ruler_pt_cwe_2048_stderr: 0.009549096842162718
|
|
ruler_pt_cwe_4096: 0.186
|
|
ruler_pt_cwe_4096_stderr: N/A
|
|
ruler_pt_cwe_alias: " - ruler_pt_cwe"
|
|
ruler_pt_fwe_1024: 0.6753333333333332
|
|
ruler_pt_fwe_1024_stderr: 0.01312227747420385
|
|
ruler_pt_fwe_2048: 0.5393333333333332
|
|
ruler_pt_fwe_2048_stderr: 0.012449640261503029
|
|
ruler_pt_fwe_4096: 0.494
|
|
ruler_pt_fwe_4096_stderr: N/A
|
|
ruler_pt_fwe_alias: " - ruler_pt_fwe"
|
|
ruler_pt_vt_1024: 0.9276
|
|
ruler_pt_vt_1024_stderr: 0.01029798898592869
|
|
ruler_pt_vt_2048: 0.9256
|
|
ruler_pt_vt_2048_stderr: 0.009345799480829435
|
|
ruler_pt_vt_4096: 0.8623999999999999
|
|
ruler_pt_vt_4096_stderr: N/A
|
|
ruler_pt_vt_alias: " - ruler_pt_vt"
|