{
  "_name_or_path": "openai/whisper-tiny",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": false,
  "architectures": [
    "WhisperForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": null,
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "d_model": 384,
  "decoder_attention_heads": 6,
  "decoder_ffn_dim": 1536,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 4,
  "decoder_start_token_id": 50258,
  "dropout": 0.0,
  "encoder_attention_heads": 6,
  "encoder_ffn_dim": 1536,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 4,
  "eos_token_id": 50257,
  "forced_decoder_ids": null,
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_prob": 0.05,
  "max_length": null,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "median_filter_width": 7,
  "model_type": "whisper",
  "num_hidden_layers": 4,
  "num_mel_bins": 80,
  "pad_token_id": 50257,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 128,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": 2.3172346830253385,
    "ignore": [],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {
      "format": "dense",
      "global_sparsity": 0.21430952951684026,
      "ignore": [
        "model.encoder.layers.0.self_attn.v_proj",
        "model.encoder.layers.0.self_attn.q_proj",
        "model.encoder.layers.0.self_attn.out_proj",
        "model.encoder.layers.0.fc1",
        "model.encoder.layers.0.fc2",
        "model.encoder.layers.1.self_attn.k_proj",
        "model.encoder.layers.1.self_attn.v_proj",
        "model.encoder.layers.1.self_attn.q_proj",
        "model.encoder.layers.1.self_attn.out_proj",
        "model.encoder.layers.1.fc1",
        "model.encoder.layers.1.fc2",
        "model.encoder.layers.2.self_attn.k_proj",
        "model.encoder.layers.2.self_attn.v_proj",
        "model.encoder.layers.2.self_attn.q_proj",
        "model.encoder.layers.2.self_attn.out_proj",
        "model.encoder.layers.2.fc1",
        "model.encoder.layers.2.fc2",
        "model.encoder.layers.3.self_attn.k_proj",
        "model.encoder.layers.3.self_attn.v_proj",
        "model.encoder.layers.3.self_attn.q_proj",
        "model.encoder.layers.3.self_attn.out_proj",
        "model.encoder.layers.3.fc1",
        "model.encoder.layers.3.fc2",
        "model.decoder.layers.0.self_attn.k_proj",
        "model.decoder.layers.0.self_attn.v_proj",
        "model.decoder.layers.0.self_attn.q_proj",
        "model.decoder.layers.0.self_attn.out_proj",
        "model.decoder.layers.0.encoder_attn.k_proj",
        "model.decoder.layers.0.encoder_attn.v_proj",
        "model.decoder.layers.0.encoder_attn.q_proj",
        "model.decoder.layers.0.encoder_attn.out_proj",
        "model.decoder.layers.0.fc1",
        "model.decoder.layers.0.fc2",
        "model.decoder.layers.1.self_attn.k_proj",
        "model.decoder.layers.1.self_attn.v_proj",
        "model.decoder.layers.1.self_attn.q_proj",
        "model.decoder.layers.1.self_attn.out_proj",
        "model.decoder.layers.1.encoder_attn.k_proj",
        "model.decoder.layers.1.encoder_attn.v_proj",
        "model.decoder.layers.1.encoder_attn.q_proj",
        "model.decoder.layers.1.encoder_attn.out_proj",
        "model.decoder.layers.1.fc1",
        "model.decoder.layers.1.fc2",
        "model.decoder.layers.2.self_attn.k_proj",
        "model.decoder.layers.2.self_attn.v_proj",
        "model.decoder.layers.2.self_attn.q_proj",
        "model.decoder.layers.2.self_attn.out_proj",
        "model.decoder.layers.2.encoder_attn.k_proj",
        "model.decoder.layers.2.encoder_attn.v_proj",
        "model.decoder.layers.2.encoder_attn.q_proj",
        "model.decoder.layers.2.encoder_attn.out_proj",
        "model.decoder.layers.2.fc1",
        "model.decoder.layers.2.fc2",
        "model.decoder.layers.3.self_attn.k_proj",
        "model.decoder.layers.3.self_attn.v_proj",
        "model.decoder.layers.3.self_attn.q_proj",
        "model.decoder.layers.3.self_attn.out_proj",
        "model.decoder.layers.3.encoder_attn.k_proj",
        "model.decoder.layers.3.encoder_attn.v_proj",
        "model.decoder.layers.3.encoder_attn.q_proj",
        "model.decoder.layers.3.encoder_attn.out_proj",
        "model.decoder.layers.3.fc1",
        "model.decoder.layers.3.fc2",
        "proj_out"
      ],
      "registry_requires_subclass": false,
      "sparsity_structure": "unstructured",
      "targets": [
        "model.encoder.layers.0.self_attn.k_proj"
      ]
    }
  },
  "scale_embedding": false,
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51865
}