{
  "model_info": {
    "name": "Yi-1.5-9B-32K",
    "id": "01-ai/Yi-1.5-9B-32K",
    "developer": "01-ai",
    "inference_platform": "unknown",
    "additional_details": {
      "precision": "bfloat16",
      "architecture": "LlamaForCausalLM",
      "params_billions": "8.829"
    }
  },
  "evaluations": [
    {
      "evaluation_id": "hfopenllm_v2/01-ai_Yi-1.5-9B-32K/1773936498.240187",
      "retrieved_timestamp": "1773936498.240187",
      "source_metadata": {
        "source_name": "HF Open LLM v2",
        "source_type": "documentation",
        "source_organization_name": "Hugging Face",
        "evaluator_relationship": "third_party"
      },
      "eval_library": {
        "name": "lm-evaluation-harness",
        "version": "0.4.0",
        "additional_details": {
          "fork": "https://github.com/huggingface/lm-evaluation-harness/tree/adding_all_changess"
        }
      },
      "benchmark": "hfopenllm_v2",
      "evaluation_results": [
        {
          "evaluation_name": "IFEval",
          "source_data": {
            "dataset_name": "IFEval",
            "source_type": "hf_dataset",
            "hf_repo": "google/IFEval"
          },
          "metric_config": {
            "evaluation_description": "Accuracy on IFEval",
            "lower_is_better": false,
            "score_type": "continuous",
            "min_score": 0.0,
            "max_score": 1.0
          },
          "score_details": {
            "score": 0.2303
          }
        },
        {
          "evaluation_name": "BBH",
          "source_data": {
            "dataset_name": "BBH",
            "source_type": "hf_dataset",
            "hf_repo": "SaylorTwift/bbh"
          },
          "metric_config": {
            "evaluation_description": "Accuracy on BBH",
            "lower_is_better": false,
            "score_type": "continuous",
            "min_score": 0.0,
            "max_score": 1.0
          },
          "score_details": {
            "score": 0.4963
          }
        },
        {
          "evaluation_name": "MATH Level 5",
          "source_data": {
            "dataset_name": "MATH Level 5",
            "source_type": "hf_dataset",
            "hf_repo": "DigitalLearningGmbH/MATH-lighteval"
          },
          "metric_config": {
            "evaluation_description": "Exact Match on MATH Level 5",
            "lower_is_better": false,
            "score_type": "continuous",
            "min_score": 0.0,
            "max_score": 1.0
          },
          "score_details": {
            "score": 0.108
          }
        },
        {
          "evaluation_name": "GPQA",
          "source_data": {
            "dataset_name": "GPQA",
            "source_type": "hf_dataset",
            "hf_repo": "Idavidrein/gpqa"
          },
          "metric_config": {
            "evaluation_description": "Accuracy on GPQA",
            "lower_is_better": false,
            "score_type": "continuous",
            "min_score": 0.0,
            "max_score": 1.0
          },
          "score_details": {
            "score": 0.3591
          }
        },
        {
          "evaluation_name": "MUSR",
          "source_data": {
            "dataset_name": "MUSR",
            "source_type": "hf_dataset",
            "hf_repo": "TAUR-Lab/MuSR"
          },
          "metric_config": {
            "evaluation_description": "Accuracy on MUSR",
            "lower_is_better": false,
            "score_type": "continuous",
            "min_score": 0.0,
            "max_score": 1.0
          },
          "score_details": {
            "score": 0.4186
          }
        },
        {
          "evaluation_name": "MMLU-PRO",
          "source_data": {
            "dataset_name": "MMLU-PRO",
            "source_type": "hf_dataset",
            "hf_repo": "TIGER-Lab/MMLU-Pro"
          },
          "metric_config": {
            "evaluation_description": "Accuracy on MMLU-PRO",
            "lower_is_better": false,
            "score_type": "continuous",
            "min_score": 0.0,
            "max_score": 1.0
          },
          "score_details": {
            "score": 0.3765
          }
        }
      ],
      "detailed_evaluation_results": null,
      "generation_config": null
    }
  ]
}