119 lines
3.3 KiB
JSON
119 lines
3.3 KiB
JSON
{
|
|
"type": "workbench_hf_jobs",
|
|
"model": "Nanthasit/sakthai-context-7b-merged",
|
|
"load_time_seconds": 137.3,
|
|
"device": "cuda:0",
|
|
"gpu": "Tesla T4",
|
|
"vram_used_gb": 5.56,
|
|
"timestamp": "2026-07-07T14:44:33Z",
|
|
"results": [
|
|
{
|
|
"name": "basic_greeting",
|
|
"passed": true,
|
|
"response_preview": "Hello!",
|
|
"response_length": 6,
|
|
"latency_seconds": 1.08,
|
|
"prompt_tokens": 31,
|
|
"completion_tokens": 3,
|
|
"checks": [
|
|
"non_empty"
|
|
]
|
|
},
|
|
{
|
|
"name": "tool_call_intent",
|
|
"passed": true,
|
|
"response_preview": "Searching for the latest AI news...",
|
|
"response_length": 35,
|
|
"latency_seconds": 0.93,
|
|
"prompt_tokens": 37,
|
|
"completion_tokens": 8,
|
|
"checks": [
|
|
"non_empty",
|
|
"substantial"
|
|
]
|
|
},
|
|
{
|
|
"name": "name_recall",
|
|
"passed": true,
|
|
"response_preview": "Your name is Beer.",
|
|
"response_length": 18,
|
|
"latency_seconds": 0.78,
|
|
"prompt_tokens": 45,
|
|
"completion_tokens": 6,
|
|
"checks": [
|
|
"non_empty",
|
|
"substantial",
|
|
"name_recall"
|
|
]
|
|
},
|
|
{
|
|
"name": "factual_qa",
|
|
"passed": true,
|
|
"response_preview": "Tokyo.",
|
|
"response_length": 6,
|
|
"latency_seconds": 0.63,
|
|
"prompt_tokens": 28,
|
|
"completion_tokens": 4,
|
|
"checks": [
|
|
"non_empty",
|
|
"correct"
|
|
]
|
|
},
|
|
{
|
|
"name": "json_output",
|
|
"passed": true,
|
|
"response_preview": "{\"frameworks\": [\"TensorFlow\", \"PyTorch\", \"Keras\"]}",
|
|
"response_length": 50,
|
|
"latency_seconds": 1.62,
|
|
"prompt_tokens": 41,
|
|
"completion_tokens": 18,
|
|
"checks": [
|
|
"non_empty",
|
|
"substantial",
|
|
"valid_json"
|
|
]
|
|
},
|
|
{
|
|
"name": "instruction_following",
|
|
"passed": true,
|
|
"response_preview": "A transformer is an electrical device that transfers electrical energy between two or more circuits through inductively coupled conductors\u2014called windings\u2014without any physical connection between the c",
|
|
"response_length": 208,
|
|
"latency_seconds": 2.94,
|
|
"prompt_tokens": 29,
|
|
"completion_tokens": 36,
|
|
"checks": [
|
|
"non_empty",
|
|
"substantial"
|
|
]
|
|
},
|
|
{
|
|
"name": "multi_step_reasoning",
|
|
"passed": true,
|
|
"response_preview": "Let's break this down step by step:\n\n1. You start with 3 apples.\n2. You give away 1 apple: 3 - 1 = 2 apples remaining.\n3. You buy 5 more apples: 2 + 5 = 7 apples.\n\nSo, you end up with 7 apples.",
|
|
"response_length": 193,
|
|
"latency_seconds": 5.21,
|
|
"prompt_tokens": 50,
|
|
"completion_tokens": 68,
|
|
"checks": [
|
|
"non_empty",
|
|
"substantial",
|
|
"correct_answer"
|
|
]
|
|
},
|
|
{
|
|
"name": "context_window",
|
|
"passed": true,
|
|
"response_preview": "The paper \"Attention Is All You Need\" was published in 2017. It introduced the transformer architecture which has since become a fundamental building block for many state-of-the-art natural language p",
|
|
"response_length": 246,
|
|
"latency_seconds": 4.45,
|
|
"prompt_tokens": 65,
|
|
"completion_tokens": 54,
|
|
"checks": [
|
|
"non_empty",
|
|
"substantial",
|
|
"correct_answer"
|
|
]
|
|
}
|
|
],
|
|
"summary": "8/8 passed"
|
|
} |