eval-results/demo-leaderboard/gte-qwen2-1.5b_yi15-34b/results_2023-12-08 15:46:20.425378.json

{
  "results": {
    "retrieval": {
      "mrr": 0.36173120728929387,
      "map": 0.3512338648443432
    },
    "generation": {
      "em": 0.0,
      "f1": 0.16041349053275844,
      "rouge1": 0.21775697114621573,
      "rouge2": 0.09738983880706074,
      "rougeL": 0.08775246194460379,
      "accuracy": 0.3211845102505695,
      "completeness": 0.5703789636504254,
      "hallucination": 0.07665094339622641,
      "utilization": 0.40828402366863903,
      "numerical_accuracy": 0.162
    }
  },
  "config": {
    "eval_name": "gte-qwen2-1.5b_yi15-34b",
    "generation_model": "01ai/Yi-1.5-34B-Chat-16K",
    "generation_model_args": {
      "name": "01ai/Yi-1.5-34B-Chat-16K",
      "num_params": 34,
      "open_source": true
    },
    "retrieval_model": "Alibaba-NLP/gte-Qwen2-1.5B-instruct",
    "retrieval_model_args": {
      "name": "Alibaba-NLP/gte-Qwen2-1.5B-instruct",
      "num_params": 1.5,
      "open_source": true
    }
  }
}