{
  "activation_function": "gelu_new",
  "alae_activation": "gelu",
  "alae_depth": 3,
  "alae_dilation_growth_rate": 3,
  "alae_dim_feedforward": 2048,
  "alae_dropout": 0.05,
  "alae_hidden_dim": 512,
  "alae_max_decode_len": 256,
  "alae_nhead": 8,
  "alae_norm": null,
  "alae_num_decoder_layers": 4,
  "alae_num_encoder_layers": 4,
  "alae_num_res_blocks": 2,
  "architectures": [
    "MugenForConditionalGeneration"
  ],
  "attn_pdrop": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_mugen.MugenConfig",
    "AutoModelForCausalLM": "modeling_mugen.MugenForConditionalGeneration"
  },
  "bos_token_id": 50256,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "eval_sample_temperature": 1.0,
  "fps": 20,
  "initializer_range": 0.02,
  "k_latent_slots": 2,
  "latent_dim": 512,
  "latent_low_rank": 64,
  "layer_norm_epsilon": 1e-05,
  "length_multiple": 4,
  "m2t_max_new_tokens": 64,
  "m2t_num_beams": 1,
  "m2t_prompt_prefix": "Please describe the following human motion using plain text:",
  "model_type": "mugen",
  "mot_token": "<MOT>",
  "mot_token_id": 50260,
  "motion_input_dim": 263,
  "n_embd": 768,
  "n_head": 12,
  "n_inner": null,
  "n_layer": 12,
  "n_positions": 1024,
  "num_cross_attn_layers": 2,
  "num_joints": 22,
  "pad_token_id": 50256,
  "resid_pdrop": 0.1,
  "router_delta_scale": 4.0,
  "router_eval_tau": 1.5,
  "router_hidden": 512,
  "router_static_scale": 4.0,
  "t2m_prompt_template": "Please generate human motion based on the following textual description: {text} {mot}",
  "torch_dtype": "float32",
  "transformers_version": "4.51.0",
  "vocab_size": 50261
}