pruning_info.json

{
  "base_model": "HuggingFaceTB/SmolVLM-Instruct",
  "method": "layer_pruning_shortgpt_bi_score",
  "layers_removed": [
    20
  ],
  "n_layers_original": 24,
  "n_layers_remaining": 23,
  "params_before_M": 2246.3,
  "params_after_M": 2179.2,
  "param_reduction_pct": 3.0,
  "benchmarks": {
    "vqav2": {
      "accuracy": 0.6067,
      "avg_latency_s": 0.3516,
      "peak_memory_mb": 5643.1,
      "avg_memory_mb": 5637.0,
      "throughput_sps": 2.841,
      "avg_power_w": 208.4,
      "avg_gpu_util_pct": 58.8,
      "n_samples": 50,
      "n_evaluated": 50,
      "n_skipped": 0,
      "all_failed": false,
      "zero_accuracy_warning": false,
      "metrics": {
        "exact_match": 0.6067,
        "contains": 0.64,
        "token_f1": 0.6667,
        "bleu": 0.6547,
        "rouge_l": 0.6667
      }
    }
  }
}