mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-05 22:04:12 +00:00
- Caminho do compartimento pai e CIDR do SSH saem do código para .secrets/oci-settings.json (fora do Git), com override por DMB_*. - Relatórios de sanidade deixam de gravar o hostname local. - tests/test_sensitive.py falha se OCIDs, chaves, IPs públicos ou valores de .secrets aparecerem em arquivos versionados. - tools/plan_progress.py gera o bloco de andamento por fase no plano. - Plano: status reais das tarefas de F0, F3 e F6; README e docs/05 com GPU em sa-saopaulo-1, runtime CUDA do Rizzo e pipeline sintético. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
219 lines
5.1 KiB
JSON
219 lines
5.1 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "laya",
|
|
"model_id": "laya@1720e3e3357c",
|
|
"revision": "1720e3e3357cfe1e281542e223f8273b0890ca34",
|
|
"adapter_version": "0.1.0",
|
|
"device": "cpu",
|
|
"context_limit": 1024,
|
|
"probabilities_source": "native"
|
|
},
|
|
"device": "cpu",
|
|
"load_seconds": 8.4,
|
|
"conformance": [
|
|
{
|
|
"name": "valid_choice_noul",
|
|
"expected": "ok",
|
|
"got": "ok"
|
|
},
|
|
{
|
|
"name": "valid_score",
|
|
"expected": "ok",
|
|
"got": "ok"
|
|
},
|
|
{
|
|
"name": "valid_state_object",
|
|
"expected": "ok",
|
|
"got": "ok"
|
|
},
|
|
{
|
|
"name": "invalid_17_options",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_single_option",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_noul_missing_false",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_unknown_type",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_empty_state",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_no_questions",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
},
|
|
{
|
|
"name": "invalid_extra_field",
|
|
"expected": "invalid_request",
|
|
"got": "invalid_request"
|
|
}
|
|
],
|
|
"sanity": [
|
|
{
|
|
"name": "choice:pagamento",
|
|
"gold": "pagamento",
|
|
"pred": "pagamento",
|
|
"latency_ms": 114.4,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "pagamento",
|
|
"confidence": 0.9977,
|
|
"probabilities": {
|
|
"pagamento": 0.9997979802020598,
|
|
"cancelamento": 1.0000980096049412e-06,
|
|
"suporte_tecnico": 1.0000980096049412e-06,
|
|
"sem_correspondencia": 0.00020001960192098824
|
|
}
|
|
},
|
|
"pred_permuted": "pagamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:cancelamento",
|
|
"gold": "cancelamento",
|
|
"pred": "cancelamento",
|
|
"latency_ms": 137.1,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "cancelamento",
|
|
"confidence": 1.0,
|
|
"probabilities": {
|
|
"pagamento": 9.99997000009e-07,
|
|
"cancelamento": 0.999997000009,
|
|
"suporte_tecnico": 9.99997000009e-07,
|
|
"sem_correspondencia": 9.99997000009e-07
|
|
}
|
|
},
|
|
"pred_permuted": "cancelamento",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:suporte_tecnico",
|
|
"gold": "suporte_tecnico",
|
|
"pred": "suporte_tecnico",
|
|
"latency_ms": 154.9,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "suporte_tecnico",
|
|
"confidence": 0.2935,
|
|
"probabilities": {
|
|
"pagamento": 0.0496049604960496,
|
|
"cancelamento": 0.047204720472047206,
|
|
"suporte_tecnico": 0.5706570657065706,
|
|
"sem_correspondencia": 0.33253325332533257
|
|
}
|
|
},
|
|
"pred_permuted": "suporte_tecnico",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "choice:sem_correspondencia",
|
|
"gold": "sem_correspondencia",
|
|
"pred": "sem_correspondencia",
|
|
"latency_ms": 115.2,
|
|
"answer": {
|
|
"type": "choice",
|
|
"choice": "sem_correspondencia",
|
|
"confidence": 0.7909,
|
|
"probabilities": {
|
|
"pagamento": 0.0034996500349965005,
|
|
"cancelamento": 0.0044995500449955,
|
|
"suporte_tecnico": 0.0642935706429357,
|
|
"sem_correspondencia": 0.9277072292770723
|
|
}
|
|
},
|
|
"pred_permuted": "sem_correspondencia",
|
|
"permutation_invariant": true,
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:clara",
|
|
"gold": "true",
|
|
"pred": "true",
|
|
"latency_ms": 99.9,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.9982
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "noul:vaga",
|
|
"gold": "false",
|
|
"pred": "false",
|
|
"latency_ms": 88.8,
|
|
"answer": {
|
|
"type": "noul",
|
|
"noul": 0.1563
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:alta",
|
|
"gold": "2",
|
|
"pred": "2",
|
|
"latency_ms": 97.6,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 1.1202,
|
|
"confidence": 0.01,
|
|
"probabilities": {
|
|
"0": 0.2718,
|
|
"1": 0.3362,
|
|
"2": 0.392
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": true
|
|
},
|
|
{
|
|
"name": "score:baixa",
|
|
"gold": "0",
|
|
"pred": "1",
|
|
"latency_ms": 91.0,
|
|
"answer": {
|
|
"type": "score",
|
|
"score": 1.0998999999999999,
|
|
"confidence": 0.1514,
|
|
"probabilities": {
|
|
"0": 0.1477,
|
|
"1": 0.6047,
|
|
"2": 0.2476
|
|
},
|
|
"legend": {
|
|
"0": "Baixa",
|
|
"1": "Média",
|
|
"2": "Alta"
|
|
}
|
|
},
|
|
"correct": false
|
|
}
|
|
],
|
|
"summary": {
|
|
"contract_violations": [],
|
|
"sanity_correct": "7/8",
|
|
"permutation_invariant": "4/4"
|
|
}
|
|
}
|