config.json

{
  "_name_or_path": "neuralmagic/Llama-2-7b-ultrachat200k",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "sparsity_config": {
      "format": "dense",
      "global_sparsity": 0.48052908139289224,
      "ignore": [
        "lm_head"
      ],
      "registry_requires_subclass": false,
      "sparsity_structure": "2:4",
      "targets": [
        "Linear"
      ]
    },
    "version": "0.8.1.20250103"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vocab_size": 32000
}