millrace-ai's picture
Release stories511K: 235,952-byte INT4 model and research archive
3c85459 verified
Raw History Blame Contribute Delete
4.21 kB
{
"winner": "cooler",
"screen": {
"baseline": {
"complete-float": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 23,
"1": 1
},
"resolved_and_boundary": 0,
"boundary": 21,
"coherence": 0.041666666666666664
},
"released": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 18,
"coherence": 0.0
},
"complete-int4": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 20,
"coherence": 0.0
}
},
"cooler": {
"complete-float": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 21,
"coherence": 0.0
},
"released": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 20,
"coherence": 0.0
},
"complete-int4": {
"n": 24,
"resolved": 1,
"judge_grade_2": 1,
"resolution_counts": {
"0": 22,
"2": 1,
"1": 1
},
"resolved_and_boundary": 1,
"boundary": 20,
"coherence": 0.08333333333333333
}
},
"narrower": {
"complete-float": {
"n": 24,
"resolved": 1,
"judge_grade_2": 1,
"resolution_counts": {
"0": 23,
"2": 1
},
"resolved_and_boundary": 1,
"boundary": 22,
"coherence": 0.041666666666666664
},
"complete-int4": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 21,
"coherence": 0.0
},
"released": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 19,
"coherence": 0.0
}
},
"warmer": {
"complete-int4": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 20,
"coherence": 0.0
},
"complete-float": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 23,
"coherence": 0.0
},
"released": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 17,
"coherence": 0.0
}
},
"wider": {
"complete-int4": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 22,
"coherence": 0.0
},
"released": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 20,
"coherence": 0.0
},
"complete-float": {
"n": 24,
"resolved": 0,
"judge_grade_2": 0,
"resolution_counts": {
"0": 24
},
"resolved_and_boundary": 0,
"boundary": 22,
"coherence": 0.0
}
}
},
"confirmation_settings": [
"baseline",
"cooler"
]
}