mirror of https://github.com/aliasrobotics/cai.git
testing yml
This commit is contained in:
parent
c79a51d71f
commit
61b07f9838
|
|
@ -1,12 +0,0 @@
|
|||
CyberMetric Evaluation
|
||||
=====================
|
||||
|
||||
Model: ollama/qwen2.5:14b
|
||||
Dataset: CyberMetric-2-v1.json
|
||||
Start Time: 2025-05-08 12:31:39
|
||||
Status: Completed
|
||||
Questions Processed: 2
|
||||
Correct Answers: 1
|
||||
Accuracy: 50.00%
|
||||
End Time: 2025-05-08 12:31:42
|
||||
Duration: 0:00:02.434703
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"questions": [
|
||||
{
|
||||
"question": "Which of the following is a desirable property of a biometric system?",
|
||||
"answers": {
|
||||
"A": "Permanent",
|
||||
"B": "Transferability",
|
||||
"C": "Uniformity",
|
||||
"D": "Forgiveness"
|
||||
},
|
||||
"solution": "A",
|
||||
"llm_answer": "C"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
CyberMetric Evaluation
|
||||
=====================
|
||||
|
||||
Model: ollama/qwen2.5:14b
|
||||
Dataset: CyberMetric-2-v1.json
|
||||
Start Time: 2025-05-08 12:23:35
|
||||
Status: Completed
|
||||
Questions Processed: 2
|
||||
Correct Answers: 1
|
||||
Accuracy: 50.00%
|
||||
End Time: 2025-05-08 12:23:38
|
||||
Duration: 0:00:02.306513
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"questions": [
|
||||
{
|
||||
"question": "Which of the following is a desirable property of a biometric system?",
|
||||
"answers": {
|
||||
"A": "Permanent",
|
||||
"B": "Transferability",
|
||||
"C": "Uniformity",
|
||||
"D": "Forgiveness"
|
||||
},
|
||||
"solution": "A",
|
||||
"llm_answer": "C"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
CyberMetric Evaluation
|
||||
=====================
|
||||
|
||||
Model: ollama/qwen2.5:14b
|
||||
Dataset: CyberMetric-2-v1.json
|
||||
Start Time: 2025-05-08 12:22:51
|
||||
Status: Running
|
||||
Questions Processed: 0
|
||||
Correct Answers: 0
|
||||
Accuracy: 0.00%
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
CyberMetric Evaluation
|
||||
=====================
|
||||
|
||||
Model: openrouter/qwen/qwen3-32b:free
|
||||
Dataset: CyberMetric-2-v1.json
|
||||
Start Time: 2025-05-08 12:23:53
|
||||
Status: Running
|
||||
Questions Processed: 0
|
||||
Correct Answers: 0
|
||||
Accuracy: 0.00%
|
||||
|
|
@ -0,0 +1 @@
|
|||
Subproject commit 2d82e92dd6171a3fd5b40f8306af3b8c366179e6
|
||||
|
|
@ -1,11 +1,11 @@
|
|||
use_base_container: &use_base_container
|
||||
stage: test
|
||||
stage: benchmark
|
||||
image: "${CI_REGISTRY_IMAGE}:latest"
|
||||
services:
|
||||
- name: docker:dind
|
||||
alias: docker
|
||||
|
||||
run_benchmark: &run_benchmark
|
||||
.run_benchmark: &run_benchmark
|
||||
<<: *use_base_container
|
||||
script:
|
||||
- pip3 install -e .
|
||||
|
|
@ -14,7 +14,7 @@ run_benchmark: &run_benchmark
|
|||
paths:
|
||||
- benchmarks/seceval/eval/outputs/
|
||||
- benchmarks/cybermetric/outputs/
|
||||
expire_in: 1 month
|
||||
expire_in: 12 month
|
||||
tags:
|
||||
- p40
|
||||
- x86
|
||||
|
|
@ -22,7 +22,7 @@ run_benchmark: &run_benchmark
|
|||
- if: $CI_COMMIT_BRANCH
|
||||
when: on_success
|
||||
|
||||
🛠️ benchmark test_eval:
|
||||
🛠️ benchmark test_seceval:
|
||||
<<: *run_benchmark
|
||||
variables:
|
||||
OLLAMA_API_BASE: "http://localhost:8000"
|
||||
|
|
|
|||
Loading…
Reference in New Issue