Delete v6_5_v2_user_questions.json with huggingface_hub
Browse files- v6_5_v2_user_questions.json +0 -82
v6_5_v2_user_questions.json
DELETED
|
@@ -1,82 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"evaluation": "user_questions_without_help_v65_v2",
|
| 3 |
-
"user_requirement": "não ajudar o modelo em respostas e lançar perguntas",
|
| 4 |
-
"questions_sent_verbatim": true,
|
| 5 |
-
"no_context_added": true,
|
| 6 |
-
"no_system_prompt": true,
|
| 7 |
-
"no_few_shot": true,
|
| 8 |
-
"n_questions": 3,
|
| 9 |
-
"questions": [
|
| 10 |
-
"Luva de Pedreiro Távila",
|
| 11 |
-
"Lula reserva valor",
|
| 12 |
-
"Amazonas força-tarefa vítimas"
|
| 13 |
-
],
|
| 14 |
-
"results": [
|
| 15 |
-
{
|
| 16 |
-
"query": "Luva de Pedreiro Távila",
|
| 17 |
-
"query_was_modified": false,
|
| 18 |
-
"context_provided": false,
|
| 19 |
-
"system_prompt_used": false,
|
| 20 |
-
"few_shot_examples": false,
|
| 21 |
-
"som_prediction": "long_text",
|
| 22 |
-
"reasoning_length": 68,
|
| 23 |
-
"has_think": false,
|
| 24 |
-
"has_plan": false,
|
| 25 |
-
"has_answer": true,
|
| 26 |
-
"has_decompose": false,
|
| 27 |
-
"think_preview": "",
|
| 28 |
-
"answer_preview": "ReasoningEngine disabled. SOM prediction: long_text",
|
| 29 |
-
"raw_response_preview": "<answer>ReasoningEngine disabled. SOM prediction: long_text</answer>",
|
| 30 |
-
"n_tags": 1,
|
| 31 |
-
"latency_ms": 28.188228607177734
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"query": "Lula reserva valor",
|
| 35 |
-
"query_was_modified": false,
|
| 36 |
-
"context_provided": false,
|
| 37 |
-
"system_prompt_used": false,
|
| 38 |
-
"few_shot_examples": false,
|
| 39 |
-
"som_prediction": "short_text",
|
| 40 |
-
"reasoning_length": 69,
|
| 41 |
-
"has_think": false,
|
| 42 |
-
"has_plan": false,
|
| 43 |
-
"has_answer": true,
|
| 44 |
-
"has_decompose": false,
|
| 45 |
-
"think_preview": "",
|
| 46 |
-
"answer_preview": "ReasoningEngine disabled. SOM prediction: short_text",
|
| 47 |
-
"raw_response_preview": "<answer>ReasoningEngine disabled. SOM prediction: short_text</answer>",
|
| 48 |
-
"n_tags": 1,
|
| 49 |
-
"latency_ms": 5.802154541015625
|
| 50 |
-
},
|
| 51 |
-
{
|
| 52 |
-
"query": "Amazonas força-tarefa vítimas",
|
| 53 |
-
"query_was_modified": false,
|
| 54 |
-
"context_provided": false,
|
| 55 |
-
"system_prompt_used": false,
|
| 56 |
-
"few_shot_examples": false,
|
| 57 |
-
"som_prediction": "short_text",
|
| 58 |
-
"reasoning_length": 69,
|
| 59 |
-
"has_think": false,
|
| 60 |
-
"has_plan": false,
|
| 61 |
-
"has_answer": true,
|
| 62 |
-
"has_decompose": false,
|
| 63 |
-
"think_preview": "",
|
| 64 |
-
"answer_preview": "ReasoningEngine disabled. SOM prediction: short_text",
|
| 65 |
-
"raw_response_preview": "<answer>ReasoningEngine disabled. SOM prediction: short_text</answer>",
|
| 66 |
-
"n_tags": 1,
|
| 67 |
-
"latency_ms": 5.597352981567383
|
| 68 |
-
}
|
| 69 |
-
],
|
| 70 |
-
"summary": {
|
| 71 |
-
"n_with_answer": 3,
|
| 72 |
-
"n_with_think": 0,
|
| 73 |
-
"answer_rate": 1.0,
|
| 74 |
-
"think_rate": 0.0,
|
| 75 |
-
"avg_latency_ms": 13.19591204325358,
|
| 76 |
-
"avg_reasoning_length": 68.66666666666667
|
| 77 |
-
},
|
| 78 |
-
"quality_assessment": {
|
| 79 |
-
"model_not_helped": true,
|
| 80 |
-
"note": "As 3 perguntas foram enviadas verbatim, sem system prompt, sem few-shot, sem contexto adicional."
|
| 81 |
-
}
|
| 82 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|