{
  "_name_or_path": "lmsys/vicuna-7b-v1.5-16k",
  "architectures": [
    "WrappedLlamav2ForCausalLM"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "max_sequence_length": 16384,
  "mm_hidden_size": 512,
  "mm_use_audio_start_end": true,
  "model_type": "wrapped_llamav2",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 4.0,
    "type": "linear"
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.30.0",
  "tune_mm_mlp_adapter": true,
  "use_cache": false,
  "use_mm_proj": true,
  "vocab_size": 32003
}