{
  "_name_or_path": "/root/.cache/huggingface/hub/models--neuralmagic--SparseLlama-2-7b-cnn-daily-mail-pruned_50.2of4/snapshots/9f5abdaba734b6ff492723a824ee4c9c269da61a",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.40.0",
  "use_cache": true,
  "vocab_size": 32000,
  "quantization_config": {
    "quantization_config": {
      "config_groups": {
        "group_0": {
          "input_activations": null,
          "output_activations": null,
          "targets": [
            "Linear"
          ],
          "weights": {
            "block_structure": null,
            "dynamic": false,
            "group_size": null,
            "num_bits": 4,
            "observer": "minmax",
            "observer_kwargs": {},
            "strategy": "channel",
            "symmetric": true,
            "type": "int"
          }
        }
      },
      "format": "pack-quantized",
      "global_compression_ratio": 1.8983383764912574,
      "ignore": [
        "lm_head"
      ],
      "quant_method": "sparseml",
      "quantization_status": "frozen"
    },
    "sparsity_config": {
      "format": "dense",
      "global_sparsity": 53.93040953679281,
      "registry_requires_subclass": false,
      "sparsity_structure": "unstructured"
    },
    "quant_method": "compressed-tensors"
  }
}