Files
RuadaptQwen2.5-1.5B-instruct/llmtf_eval/darumeru_MultiQ_total.jsonl

9 lines
178 B
Plaintext
Raw Normal View History

{
"task_name": "darumeru/MultiQ",
"results": {
"f1": 0.3016876852043635,
"em": 0.21319311663479923
},
"leaderboard_result": 0.25744040091958137
}