83 lines
3.2 KiB
YAML
83 lines
3.2 KiB
YAML
model_name: Tucano2-qwen-1.5B-Think
|
|
results:
|
|
niah_pt_multikey_1_1024: 0.706
|
|
niah_pt_multikey_1_1024_stderr: 0.02039509548493655
|
|
niah_pt_multikey_1_2048: 0.67
|
|
niah_pt_multikey_1_2048_stderr: 0.021049612166134782
|
|
niah_pt_multikey_1_4096: 0.542
|
|
niah_pt_multikey_1_4096_stderr: N/A
|
|
niah_pt_multikey_1_alias: " - niah_pt_multikey_1"
|
|
niah_pt_multikey_2_1024: 0.48
|
|
niah_pt_multikey_2_1024_stderr: 0.022365160424231326
|
|
niah_pt_multikey_2_2048: 0.238
|
|
niah_pt_multikey_2_2048_stderr: 0.019064072958198387
|
|
niah_pt_multikey_2_4096: 0.062
|
|
niah_pt_multikey_2_4096_stderr: N/A
|
|
niah_pt_multikey_2_alias: " - niah_pt_multikey_2"
|
|
niah_pt_multikey_3_1024: 0.486
|
|
niah_pt_multikey_3_1024_stderr: 0.022374298166353144
|
|
niah_pt_multikey_3_2048: 0.31
|
|
niah_pt_multikey_3_2048_stderr: 0.020704041021724684
|
|
niah_pt_multikey_3_4096: 0.184
|
|
niah_pt_multikey_3_4096_stderr: N/A
|
|
niah_pt_multikey_3_alias: " - niah_pt_multikey_3"
|
|
niah_pt_multiquery_1024: 0.531
|
|
niah_pt_multiquery_1024_stderr: 0.013691344193015646
|
|
niah_pt_multiquery_2048: 0.4915
|
|
niah_pt_multiquery_2048_stderr: 0.014053487147395266
|
|
niah_pt_multiquery_4096: 0.4215
|
|
niah_pt_multiquery_4096_stderr: N/A
|
|
niah_pt_multiquery_alias: " - niah_pt_multiquery"
|
|
niah_pt_multivalue_1024: 0.4995
|
|
niah_pt_multivalue_1024_stderr: 0.013476376569794338
|
|
niah_pt_multivalue_2048: 0.519
|
|
niah_pt_multivalue_2048_stderr: 0.013327913059930505
|
|
niah_pt_multivalue_4096: 0.4545
|
|
niah_pt_multivalue_4096_stderr: N/A
|
|
niah_pt_multivalue_alias: " - niah_pt_multivalue"
|
|
niah_pt_single_1_1024: 0.82
|
|
niah_pt_single_1_1024_stderr: 0.017198592476314233
|
|
niah_pt_single_1_2048: 0.816
|
|
niah_pt_single_1_2048_stderr: 0.017346174781752842
|
|
niah_pt_single_1_4096: 0.8
|
|
niah_pt_single_1_4096_stderr: N/A
|
|
niah_pt_single_1_alias: " - niah_pt_single_1"
|
|
niah_pt_single_2_1024: 0.778
|
|
niah_pt_single_2_1024_stderr: 0.018604414758250098
|
|
niah_pt_single_2_2048: 0.772
|
|
niah_pt_single_2_2048_stderr: 0.018781306529363172
|
|
niah_pt_single_2_4096: 0.688
|
|
niah_pt_single_2_4096_stderr: N/A
|
|
niah_pt_single_2_alias: " - niah_pt_single_2"
|
|
niah_pt_single_3_1024: 0.468
|
|
niah_pt_single_3_1024_stderr: 0.022337186479044296
|
|
niah_pt_single_3_2048: 0.508
|
|
niah_pt_single_3_2048_stderr: 0.022380208834928014
|
|
niah_pt_single_3_4096: 0.5
|
|
niah_pt_single_3_4096_stderr: N/A
|
|
niah_pt_single_3_alias: " - niah_pt_single_3"
|
|
ruler_pt_4096: 0.44008484848484847
|
|
ruler_pt_4096_stderr: N/A
|
|
ruler_pt_alias: ruler_pt
|
|
ruler_pt_cwe_1024: 0.2516
|
|
ruler_pt_cwe_1024_stderr: 0.0065879953982022075
|
|
ruler_pt_cwe_2048: 0.10560000000000001
|
|
ruler_pt_cwe_2048_stderr: 0.0046626989526502875
|
|
ruler_pt_cwe_4096: 0.268
|
|
ruler_pt_cwe_4096_stderr: N/A
|
|
ruler_pt_cwe_alias: " - ruler_pt_cwe"
|
|
ruler_pt_fwe_1024: 0.7766666666666666
|
|
ruler_pt_fwe_1024_stderr: 0.010771818051204566
|
|
ruler_pt_fwe_2048: 0.644
|
|
ruler_pt_fwe_2048_stderr: 0.010544896116732008
|
|
ruler_pt_fwe_4096: 0.5413333333333332
|
|
ruler_pt_fwe_4096_stderr: N/A
|
|
ruler_pt_fwe_alias: " - ruler_pt_fwe"
|
|
ruler_pt_vt_1024: 0.8336
|
|
ruler_pt_vt_1024_stderr: 0.01194434656352784
|
|
ruler_pt_vt_2048: 0.4344
|
|
ruler_pt_vt_2048_stderr: 0.014185758756689964
|
|
ruler_pt_vt_4096: 0.37960000000000005
|
|
ruler_pt_vt_4096_stderr: N/A
|
|
ruler_pt_vt_alias: " - ruler_pt_vt"
|