Upload benchmark_checkpoint.json with huggingface_hub
Browse files- benchmark_checkpoint.json +23 -0
benchmark_checkpoint.json
CHANGED
|
@@ -712,6 +712,29 @@
|
|
| 712 |
"combined": 36.7,
|
| 713 |
"misc": 46.7
|
| 714 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 715 |
}
|
| 716 |
]
|
| 717 |
}
|
|
|
|
| 712 |
"combined": 36.7,
|
| 713 |
"misc": 46.7
|
| 714 |
}
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"model": "Qwen/Qwen3-1.7B-GGUF (1.7B)",
|
| 718 |
+
"total": 90,
|
| 719 |
+
"date": "2026-06-19",
|
| 720 |
+
"hf_repo": "Qwen/Qwen3-1.7B-GGUF",
|
| 721 |
+
"params": 1700000000,
|
| 722 |
+
"overall_pass": 53,
|
| 723 |
+
"ft_pass": 72,
|
| 724 |
+
"temp_pass": 84,
|
| 725 |
+
"td_pass": 71,
|
| 726 |
+
"sp_pass": 84,
|
| 727 |
+
"overall_pct": 58.9,
|
| 728 |
+
"ft_pct": 80.0,
|
| 729 |
+
"temp_pct": 93.3,
|
| 730 |
+
"td_pct": 78.9,
|
| 731 |
+
"sp_pct": 93.3,
|
| 732 |
+
"categories": {
|
| 733 |
+
"filetype": 68.0,
|
| 734 |
+
"temporal": 60.0,
|
| 735 |
+
"combined": 43.3,
|
| 736 |
+
"misc": 73.3
|
| 737 |
+
}
|
| 738 |
}
|
| 739 |
]
|
| 740 |
}
|