pruning_info.json

{
  "base_model": "AIDC-AI/Ovis2-8B",
  "method": "layer_pruning_ppl",
  "method_name": "PPL-based (Shortened LLaMA)",
  "layers_removed": [
    4,
    5,
    7,
    8,
    10,
    11,
    13,
    15
  ],
  "n_layers_original": 28,
  "n_layers_remaining": 20,
  "params_before_M": 8935.3,
  "params_after_M": 7070.8,
  "param_reduction_pct": 20.9,
  "benchmarks": {
    "vqav2": {
      "accuracy": 0.0,
      "avg_latency_s": 0.5913,
      "peak_memory_mb": 18675.1,
      "avg_memory_mb": 18638.7,
      "throughput_sps": 1.69,
      "avg_power_w": 289.8,
      "avg_gpu_util_pct": 94.2,
      "n_samples": 50,
      "n_evaluated": 50,
      "n_skipped": 0,
      "all_failed": false,
      "zero_accuracy_warning": true,
      "metrics": {
        "exact_match": 0.0,
        "contains": 0.26,
        "token_f1": 0.0731,
        "bleu": 0.0457,
        "rouge_l": 0.0731
      }
    }
  }
}