83 lines
3.2 KiB
YAML
83 lines
3.2 KiB
YAML
|
model_name: Tucano2-qwen-3.7B-Instruct
|
||
|
|
results:
|
||
|
|
niah_pt_multikey_1_1024: 0.814
|
||
|
|
niah_pt_multikey_1_1024_stderr: 0.01741880678058399
|
||
|
|
niah_pt_multikey_1_2048: 0.72
|
||
|
|
niah_pt_multikey_1_2048_stderr: 0.020099950647503192
|
||
|
|
niah_pt_multikey_1_4096: 0.684
|
||
|
|
niah_pt_multikey_1_4096_stderr: N/A
|
||
|
|
niah_pt_multikey_1_alias: ' - niah_pt_multikey_1'
|
||
|
|
niah_pt_multikey_2_1024: 0.8
|
||
|
|
niah_pt_multikey_2_1024_stderr: 0.017906459241433807
|
||
|
|
niah_pt_multikey_2_2048: 0.696
|
||
|
|
niah_pt_multikey_2_2048_stderr: 0.02059164957122494
|
||
|
|
niah_pt_multikey_2_4096: 0.61
|
||
|
|
niah_pt_multikey_2_4096_stderr: N/A
|
||
|
|
niah_pt_multikey_2_alias: ' - niah_pt_multikey_2'
|
||
|
|
niah_pt_multikey_3_1024: 0.844
|
||
|
|
niah_pt_multikey_3_1024_stderr: 0.016243636028391108
|
||
|
|
niah_pt_multikey_3_2048: 0.86
|
||
|
|
niah_pt_multikey_3_2048_stderr: 0.015533272840269705
|
||
|
|
niah_pt_multikey_3_4096: 0.782
|
||
|
|
niah_pt_multikey_3_4096_stderr: N/A
|
||
|
|
niah_pt_multikey_3_alias: ' - niah_pt_multikey_3'
|
||
|
|
niah_pt_multiquery_1024: 0.7675
|
||
|
|
niah_pt_multiquery_1024_stderr: 0.012367028211075898
|
||
|
|
niah_pt_multiquery_2048: 0.7115
|
||
|
|
niah_pt_multiquery_2048_stderr: 0.014113251494091322
|
||
|
|
niah_pt_multiquery_4096: 0.677
|
||
|
|
niah_pt_multiquery_4096_stderr: N/A
|
||
|
|
niah_pt_multiquery_alias: ' - niah_pt_multiquery'
|
||
|
|
niah_pt_multivalue_1024: 0.769
|
||
|
|
niah_pt_multivalue_1024_stderr: 0.011425369935206152
|
||
|
|
niah_pt_multivalue_2048: 0.5945
|
||
|
|
niah_pt_multivalue_2048_stderr: 0.015011335062569266
|
||
|
|
niah_pt_multivalue_4096: 0.5215
|
||
|
|
niah_pt_multivalue_4096_stderr: N/A
|
||
|
|
niah_pt_multivalue_alias: ' - niah_pt_multivalue'
|
||
|
|
niah_pt_single_1_1024: 0.83
|
||
|
|
niah_pt_single_1_1024_stderr: 0.016815633531393464
|
||
|
|
niah_pt_single_1_2048: 0.792
|
||
|
|
niah_pt_single_1_2048_stderr: 0.01816954222122996
|
||
|
|
niah_pt_single_1_4096: 0.786
|
||
|
|
niah_pt_single_1_4096_stderr: N/A
|
||
|
|
niah_pt_single_1_alias: ' - niah_pt_single_1'
|
||
|
|
niah_pt_single_2_1024: 0.808
|
||
|
|
niah_pt_single_2_1024_stderr: 0.017632180454361004
|
||
|
|
niah_pt_single_2_2048: 0.61
|
||
|
|
niah_pt_single_2_2048_stderr: 0.021834685869369132
|
||
|
|
niah_pt_single_2_4096: 0.574
|
||
|
|
niah_pt_single_2_4096_stderr: N/A
|
||
|
|
niah_pt_single_2_alias: ' - niah_pt_single_2'
|
||
|
|
niah_pt_single_3_1024: 0.778
|
||
|
|
niah_pt_single_3_1024_stderr: 0.018604414758250098
|
||
|
|
niah_pt_single_3_2048: 0.712
|
||
|
|
niah_pt_single_3_2048_stderr: 0.02027150383507526
|
||
|
|
niah_pt_single_3_4096: 0.696
|
||
|
|
niah_pt_single_3_4096_stderr: N/A
|
||
|
|
niah_pt_single_3_alias: ' - niah_pt_single_3'
|
||
|
|
ruler_pt_4096: 0.6859484848484848
|
||
|
|
ruler_pt_4096_stderr: N/A
|
||
|
|
ruler_pt_alias: ruler_pt
|
||
|
|
ruler_pt_cwe_1024: 0.49
|
||
|
|
ruler_pt_cwe_1024_stderr: 0.0077148582667572255
|
||
|
|
ruler_pt_cwe_2048: 0.316
|
||
|
|
ruler_pt_cwe_2048_stderr: 0.006839704900524035
|
||
|
|
ruler_pt_cwe_4096: 0.562
|
||
|
|
ruler_pt_cwe_4096_stderr: N/A
|
||
|
|
ruler_pt_cwe_alias: ' - ruler_pt_cwe'
|
||
|
|
ruler_pt_fwe_1024: 0.86
|
||
|
|
ruler_pt_fwe_1024_stderr: 0.008382951812787927
|
||
|
|
ruler_pt_fwe_2048: 0.8386666666666667
|
||
|
|
ruler_pt_fwe_2048_stderr: 0.009315757857883127
|
||
|
|
ruler_pt_fwe_4096: 0.7133333333333333
|
||
|
|
ruler_pt_fwe_4096_stderr: N/A
|
||
|
|
ruler_pt_fwe_alias: ' - ruler_pt_fwe'
|
||
|
|
ruler_pt_vt_1024: 0.9887999999999999
|
||
|
|
ruler_pt_vt_1024_stderr: 0.0035005181408627236
|
||
|
|
ruler_pt_vt_2048: 0.9628
|
||
|
|
ruler_pt_vt_2048_stderr: 0.006575621460758699
|
||
|
|
ruler_pt_vt_4096: 0.9396
|
||
|
|
ruler_pt_vt_4096_stderr: N/A
|
||
|
|
ruler_pt_vt_alias: ' - ruler_pt_vt'
|