{
  "_name_or_path": "output_3b/stage_finetuning",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 24,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "sparsity_config": {
      "format": "dense",
      "global_sparsity": 0.25788666506070107,
      "ignore": [],
      "registry_requires_subclass": false,
      "sparsity_structure": "0:0",
      "targets": []
    }
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "float16",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vocab_size": 128256
}