eval-results/demo-leaderboard/gte-qwen2-1.5b_deepseek-v2-chat/results_2023-12-08 15:46:20.425378.json

{
  "results": {
    "retrieval": {
      "mrr": 0.36173120728929387,
      "map": 0.3512338648443432
    },
    "generation": {
      "em": 0.0056947608200455585,
      "f1": 0.4212862409737785,
      "rouge1": 0.3707328288930376,
      "rouge2": 0.21393113234607009,
      "rougeL": 0.2719847145278759,
      "accuracy": 0.3886674259681093,
      "completeness": 0.5858823529411765,
      "hallucination": 0.07893209518282066,
      "utilization": 0.48166472642607683,
      "numerical_accuracy": 0.27365491651205937
    }
  },
  "config": {
    "eval_name": "gte-qwen2-1.5b_deepseek-v2-chat",
    "generation_model": "deepseek-ai/DeepSeek-V2-Chat-0628",
    "generation_model_args": {
      "name": "deepseek-ai/DeepSeek-V2-Chat-0628",
      "num_params": 80,
      "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
    }
  }
}