{
  "_name_or_path": "/data2/caoty/convert/llama3",
  "architectures": [
    "LlamaPrunedForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_pruned_llama.LlamaPrunedConfig",
    "AutoModel": "modeling_pruned_llama.LlamaPrunedForCausalLM",
    "AutoModelForCausalLM": "modeling_pruned_llama.LlamaPrunedForCausalLM"
  },
  "begin_pruned_layer": 0,
  "bos_token_id": 128000,
  "context_length": 1,
  "end_pruned_layer": 32,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 7168,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "type": "dynamic"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.45.2",
  "use_cache": true,
  "vocab_size": 128256
}