{
  "alibi": false,
  "architectures": [
    "LlamaForCausalLM"
  ],
  "bos_token_id": 1,
  "dtype": "float16",
  "eos_token_id": 2,
  "fuse_attention_ffn": false,
  "fuse_attention_qkv": false,
  "fuse_sequence_parallel_allreduce": false,
  "hidden_size": 6656,
  "initializer_range": 0.02,
  "intermediate_size": 17920,
  "max_position_embeddings": 2048,
  "model_type": "llama",
  "no_recompute_layers": null,
  "num_attention_heads": 52,
  "num_hidden_layers": 60,
  "num_key_value_heads": 52,
  "pad_token_id": 0,
  "paddlenlp_version": null,
  "pp_recompute_interval": 1,
  "quantization_config": {
    "weight_quantize_algo": "weight_only_int8"
  },
  "recompute_granularity": "full",
  "rms_norm_eps": 1e-06,
  "rope_scaling_factor": 1.0,
  "rope_scaling_type": null,
  "seq_length": 2048,
  "sequence_parallel": false,
  "tensor_parallel_output": true,
  "tie_word_embeddings": false,
  "use_fused_rms_norm": false,
  "use_fused_rope": false,
  "use_recompute": false,
  "virtual_pp_degree": 1,
  "vocab_size": 32000
}