初始化项目,由ModelHub XC社区提供模型
Model: gauthierpiarrette/nl2jq-qwen3-0.6b Source: Original Platform
This commit is contained in:
25
eval_results.json
Normal file
25
eval_results.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"benchmark": "gauthierpiarrette/nl2jq-bench",
|
||||
"version": "1.0.0",
|
||||
"freeze_sha256": "25e7c01360707b30df93e7c1ed26997b3bb3ee7840a093d024bb4d16f489c5de",
|
||||
"jq_version": "1.7.1",
|
||||
"n_items": 400,
|
||||
"protocol": "one-shot; no selection or iteration against the frozen set",
|
||||
"model": "gauthierpiarrette/nl2jq-qwen3-0.6b",
|
||||
"results": [
|
||||
{
|
||||
"system": "nl2jq-qwen3-0.6b-v6",
|
||||
"decoding": "greedy",
|
||||
"pass_at_1": 0.4,
|
||||
"valid_at_1": 0.73,
|
||||
"tiers": {
|
||||
"T1": 0.65,
|
||||
"T2": 0.52,
|
||||
"T3": 0.36,
|
||||
"T4": 0.28,
|
||||
"T5": 0.2
|
||||
},
|
||||
"t5_generalization": 0.2
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user