{
  "_name_or_path": "/root/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-intermediate-step-1431k-3T/snapshots/036fa4651240b9a1487f709833b9e4b96b4c1574",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "compression_config": {
    "quantization_config": {
      "config_groups": {
        "group_0": {
          "input_activations": {
            "block_structure": null,
            "dynamic": true,
            "group_size": null,
            "num_bits": 8,
            "observer": "memoryless",
            "observer_kwargs": {},
            "strategy": "token",
            "symmetric": true,
            "type": "int"
          },
          "output_activations": null,
          "targets": [
            "Linear"
          ],
          "weights": {
            "block_structure": null,
            "dynamic": false,
            "group_size": null,
            "num_bits": 8,
            "observer": "minmax",
            "observer_kwargs": {},
            "strategy": "tensor",
            "symmetric": true,
            "type": "int"
          }
        }
      },
      "format": "int-quantized",
      "global_compression_ratio": 1.4051191328987915,
      "ignore": [
        "model.layers.0.mlp.down_proj",
        "lm_head"
      ],
      "quant_method": "sparseml",
      "quantization_status": "frozen"
    }
  },
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.39.3",
  "use_cache": true,
  "vocab_size": 32000
}