{
  "architectures": [
    "MixtralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "fuse_sequence_parallel_allreduce": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mixtral",
  "no_recompute_layers": null,
  "num_attention_heads": 32,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "num_local_experts": 8,
  "output_router_logits": false,
  "paddlenlp_version": null,
  "recompute_granularity": "full",
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "router_aux_loss_coef": 0.02,
  "seq_length": 2048,
  "sequence_parallel": false,
  "sliding_window": null,
  "tensor_parallel_output": true,
  "tie_word_embeddings": false,
  "transformers_version": "4.36.0.dev0",
  "use_fused_rope": false,
  "use_recompute": false,
  "vocab_size": 32000
}