bk1dr/qwen3-8b-code-pkpo
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bk1dr/qwen3-8b-code-pkpo
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-30 09:33:20 +08:00
commit 8060a07a88
29 changed files with 158812 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

302
eval/final_results.json Normal file
View File

@@ -0,0 +1,302 @@
{
"details": [
{
"difficulty": "hard",
"problem_id": "arc196_a",
"samples": [
{
"completion_chars": 11690,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 12444,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 12570,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 12044,
"end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
"passed": false,
"stop_seen": false,
"tool_type": null
},
{
"completion_chars": 1151,
"end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
"passed": false,
"stop_seen": false,
"tool_type": null
},
{
"completion_chars": 10895,
"end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
"passed": false,
"stop_seen": false,
"tool_type": null
}
]
},
{
"difficulty": "hard",
"problem_id": "abc398_f",
"samples": [
{
"completion_chars": 2877,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 2932,
"end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
"passed": false,
"stop_seen": true,
"tool_type": null
},
{
"completion_chars": 715,
"end": "runtime_error",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 2867,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 2538,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 2577,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
}
]
},
{
"difficulty": "easy",
"problem_id": "abc400_a",
"samples": [
{
"completion_chars": 328,
"end": "runtime_error",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 917,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 600,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 742,
"end": "ok",
"passed": true,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 808,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 820,
"end": "ok",
"passed": true,
"stop_seen": true,
"tool_type": "final"
}
]
},
{
"difficulty": "hard",
"problem_id": "arc196_c",
"samples": [
{
"completion_chars": 5294,
"end": "runtime_error",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 1689,
"end": "runtime_error",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 5976,
"end": "format_error: final",
"passed": false,
"stop_seen": false,
"tool_type": "final"
},
{
"completion_chars": 4300,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 4040,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 5089,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
}
]
},
{
"difficulty": "medium",
"problem_id": "abc400_d",
"samples": [
{
"completion_chars": 8429,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 7583,
"end": "runtime_error",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 7201,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 7008,
"end": "runtime_error",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 2737,
"end": "format_error: final",
"passed": false,
"stop_seen": false,
"tool_type": "final"
},
{
"completion_chars": 7069,
"end": "runtime_error",
"passed": false,
"stop_seen": true,
"tool_type": "final"
}
]
},
{
"difficulty": "hard",
"problem_id": "abc398_g",
"samples": [
{
"completion_chars": 11630,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 12637,
"end": "wrong_answer",
"passed": false,
"stop_seen": true,
"tool_type": "final"
},
{
"completion_chars": 4093,
"end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
"passed": false,
"stop_seen": false,
"tool_type": null
},
{
"completion_chars": 3088,
"end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
"passed": false,
"stop_seen": false,
"tool_type": null
},
{
"completion_chars": 13122,
"end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
"passed": false,
"stop_seen": false,
"tool_type": null
},
{
"completion_chars": 2073,
"end": "format_error: Could not parse 'Tool type' or 'Tool query' from the response. Ensure you output an <answer> block with 'Tool type:' and 'Tool query:'.",
"passed": false,
"stop_seen": false,
"tool_type": null
}
]
}
],
"eval_limit": 6,
"max_new_tokens": 1024,
"pass_at_1": 0.05555555555555555,
"passed_samples": 2,
"samples_per_problem": 6,
"tag": "stage1_group3",
"temperature": 1.0,
"tool_turn_limit": 1,
"top_p": 0.95,
"total_samples": 36
}